© 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

    class a: (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
    č
    -0.14
    [j
    -0.14
     __
    -0.13
     heuristic
    -0.09
    uristic
    -0.08
    py
    -0.08
    etween
    -0.07
    ax
    -0.07
    oal
    -0.06
    rontier
    -0.06
    Positive Logits
    class
    0.14
     St
    0.11
    umn
    0.10
    _start
    0.10
     low
    0.09
     start
    0.09
     left
    0.09
    _left
    0.08
    start
    0.08
     dp
    0.08
    Activations Density 57.377%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import statement

    python-code · gemini-2.5-flash-lite

    list index access (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
    č
    -0.10
    xF
    -0.10
    il
    -0.10
    utation
    -0.07
    gth
    -0.07
    ill
    -0.07
    t
    -0.06
     I
    -0.05
    ;
    -0.05
    f
    -0.05
    Positive Logits
    class
    0.08
    ree
    0.07
    ool
    0.06
    )],↵
    0.05
    "),
    0.05
    ):
    0.05
    '),
    0.05
    ore
    0.05
     -
    0.05
    raph
    0.04
    Activations Density 100.000%

    No Known Activations