© 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

    socket AF_INET address family

    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
    ail
    -0.11
    def
    -0.08
    .co
    -0.05
     input
    -0.05
    on
    -0.03
    ((
    -0.03
     t
    -0.03
    ed
    -0.03
    ble
    -0.02
    c
    -0.02
    Positive Logits
    ru
    0.10
    ¾
    0.09
    [u
    0.07
    _m
    0.07
    ir
    0.06
     u
    0.06
    u
    0.06
     v
    0.05
    ĥ
    0.05
     U
    0.05
    Activations Density 5.364%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable 'a' in comparisons

    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
     between
    -0.05
    _with
    -0.05
     it
    -0.05
     based
    -0.04
     that
    -0.04
     us
    -0.04
     with
    -0.04
     on
    -0.04
     whi
    -0.04
    _by
    -0.04
    Positive Logits
     Create
    0.04
    itial
    0.04
     continue
    0.04
    stance
    0.03
     Initialize
    0.03
     defaultdict
    0.03
    .graph
    0.03
    _graph
    0.02
    ameters
    0.02
    par
    0.02
    Activations Density 31.398%

    No Known Activations