© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `__init__` method definition

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     each
    -0.03
    _of
    -0.03
    join
    -0.02
    }:
    -0.02
     continue
    -0.02
    _to
    -0.02
     Get
    -0.02
                    ↵
    -0.01
    op
    -0.01
     -
    -0.01
    Positive Logits
                       
    0.07
     {}↵↵
    0.04
     []↵↵
    0.03
    self
    0.03
     {}↵
    0.03
                    
    0.03
     self
    0.03
     collections
    0.02
     []↵
    0.02
    mple
    0.02
    Activations Density 6.632%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable `b` in comparisons or logical operations

    python-code · gemini-2.5-flash-lite

    list element or argument (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    _i
    -0.04
    Ã
    -0.04
    bs
    -0.03
    (v
    -0.03
    fo
    -0.03
    (len
    -0.02
     by
    -0.02
    or
    -0.02
    ef
    -0.02
    c
    -0.02
    Positive Logits
    arehouse
    0.06
    udent
    0.06
    light
    0.06
    uild
    0.05
    stac
    0.05
    liver
    0.05
    rontier
    0.04
    mployee
    0.04
    ruck
    0.04
    mploye
    0.03
    Activations Density 53.090%

    No Known Activations