© 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. 20-CLT-HP
    7. 72908
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    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
    IMPORTED
    -0.77
    isContained
    -0.69
    MigrationBuilder
    -0.68
    Przypisy
    -0.60
    bearded
    -0.57
    HasForeignKey
    -0.56
    Diwedd
    -0.55
     DELLE
    -0.55
     Consumo
    -0.54
     Escor
    -0.54
    POSITIVE LOGITS
     rotating
    0.52
    bootstrapcdn
    0.50
     a
    0.50
    providedIn
    0.47
     growing
    0.43
    ASX
    0.43
    gouv
    0.43
     revolving
    0.42
     الوطنيه
    0.42
    Autoritní
    0.41
    Activations Density 0.000%

    No Known Activations