© 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

    assignment to instance attribute

    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
    alculate
    -0.07
     calculate
    -0.04
     total
    -0.04
    K
    -0.04
    ((
    -0.04
    alc
    -0.03
     sum
    -0.03
    _key
    -0.03
     break
    -0.03
     k
    -0.03
    Positive Logits
     range
    0.11
    _range
    0.04
    ange
    0.04
    range
    0.04
     bo
    0.03
    (range
    0.03
     enumerate
    0.02
     between
    0.01
    ..
    0.01
    mmon
    0.01
    Activations Density 42.468%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment statement (negative activations)

    python-code · gemini-2.5-flash-lite

    ending of string literals

    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
     break
    -0.01
    !
    -0.01
    ",↵
    -0.00
     else
    -0.00
    }
    -0.00
     j
    -0.00
    <extra_output_id:2047>
    -0.00
     di
    -0.00
    '
    0.00
    #
    0.00
    Positive Logits
     {}↵↵
    0.03
     {}↵
    0.02
     []↵↵
    0.02
     collections
    0.02
     []↵
    0.02
     typing
    0.01
    instance
    0.01
     given
    0.01
     parse
    0.01
    }↵↵
    0.01
    Activations Density 64.341%

    No Known Activations