© 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. 0-CLT-HP
    7. 39868
    Prev
    Next
    INDEX
    Explanations

    citations, code, links

    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
    UnitTesting
    -0.82
    LR
    -0.66
    brate
    -0.63
     doi
    -0.60
    lr
    -0.54
    ism
    -0.53
    참고
    -0.52
    PDOException
    -0.52
    olith
    -0.50
    ollectionView
    -0.49
    POSITIVE LOGITS
    enumi
    0.77
     صوتيه
    0.70
     BoxFit
    0.62
    enumii
    0.60
     pioggia
    0.60
     titoli
    0.59
     Económica
    0.57
     griega
    0.57
     sexuelle
    0.56
     direta
    0.55
    Activations Density 0.242%

    No Known Activations