© 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. 1-CLT-HP
    7. 9196
    Prev
    Next
    INDEX
    Explanations

    park

    np_max-act · 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
     समीक्षाओं
    -0.56
     prisonniers
    -0.52
    pares
    -0.49
    wendungen
    -0.46
     Karlsruhe
    -0.46
     trucks
    -0.46
    trucks
    -0.46
    boz
    -0.44
    izarse
    -0.44
     traductions
    -0.44
    POSITIVE LOGITS
     BoxFit
    0.93
    HasForeignKey
    0.76
    InSection
    0.75
     فريبيس
    0.73
    RetentionPolicy
    0.71
    StructEnd
    0.71
    ChildScrollView
    0.69
    IsContent
    0.68
     invokingState
    0.68
    setVerticalGroup
    0.66
    Activations Density 0.074%

    No Known Activations