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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96397
    Prev
    Next
    INDEX
    Explanations

    programming methods

    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
     call
    -0.97
    call
    -0.85
     calling
    -0.83
    Called
    -0.82
     appeler
    -0.82
     gọi
    -0.81
    Call
    -0.79
     calls
    -0.79
    CALL
    -0.78
     Calling
    -0.78
    POSITIVE LOGITS
    ToMany
    0.59
    Enllaces
    0.57
     SearchView
    0.57
    dafx
    0.55
    Referanser
    0.55
     للمعارف
    0.54
    jooq
    0.54
     defaultstate
    0.53
    TintMode
    0.52
    setof
    0.52
    Activations Density 0.016%

    No Known Activations