© 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
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.63
     članak
    -0.62
     pulumi
    -0.59
    Kjelder
    -0.57
    stateProvider
    -0.57
     ModelExpression
    -0.56
     StringTokenizer
    -0.56
    kuuta
    -0.56
    fortawesome
    -0.56
    ScopeManager
    -0.55
    POSITIVE LOGITS
     initComponents
    0.56
    )
    0.55
     Efficiency
    0.54
    )$}
    0.51
    0.51
    Supp
    0.49
    {`
    0.49
    >{"
    0.48
     Help
    0.47
    ">
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.