© 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

    num attribute of self

    python-code · gemini-2.5-flash-lite

    object or job attribute (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
     best
    -0.06
     end
    -0.06
    pected
    -0.06
     base
    -0.06
    .f
    -0.06
     goal
    -0.05
    _end
    -0.05
     destination
    -0.05
    end
    -0.05
    ross
    -0.05
    Positive Logits
    raph
    0.09
    graph
    0.06
    .graph
    0.06
     ]↵
    0.06
    etwork
    0.06
    vai
    0.06
     }↵
    0.05
    _si
    0.05
     coordinates
    0.05
    [u
    0.05
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    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
     re
    -0.03
    append
    -0.03
    i
    -0.02
    .append
    -0.02
     nx
    -0.02
     ny
    -0.02
     are
    -0.01
     []↵
    -0.01
     []↵↵
    -0.01
    _row
    -0.01
    Positive Logits
     **
    0.13
    **
    0.09
     /
    0.07
     *
    0.07
    *
    0.06
    ump
    0.04
    ens
    0.04
     time
    0.02
    alue
    0.02
    ariable
    0.02
    Activations Density 89.991%

    No Known Activations