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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13019
    Prev
    Next
    INDEX
    Explanations

    James and investigative

    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
     resourceCulture
    -0.70
    makeConstraints
    -0.69
     Chriftian
    -0.63
    RenderAtEndOf
    -0.59
     EdgeInsets
    -0.59
    iciary
    -0.57
    Сылтамалар
    -0.57
    Gambas
    -0.56
    +:+
    -0.56
    Portail
    -0.55
    POSITIVE LOGITS
    AndEndTag
    0.61
    cinogenicity
    0.54
    PreferredItem
    0.53
     AppModule
    0.50
     שוליים
    0.48
    Искәрмәләр
    0.47
    клопе
    0.46
     nahilalakip
    0.44
    Bước
    0.43
    onavir
    0.43
    Activations Density 0.056%

    No Known Activations