© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98211
    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
    CloseOperation
    -0.79
    SourceChecksum
    -0.71
    __':
    -0.69
    ChildScrollView
    -0.65
    Ikus
    -0.64
    waitKey
    -0.63
     NACIONAL
    -0.63
    SerializedSize
    -0.63
    Hochspringen
    -0.63
     שוליים
    -0.63
    POSITIVE LOGITS
    UpInside
    0.57
     indisponible
    0.53
    мку
    0.47
    didSet
    0.46
    uz
    0.42
    ジュアル
    0.41
     TPR
    0.41
     storico
    0.41
    lamabad
    0.41
    DO
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.