© 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. 43975
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     decide
    -0.63
     decision
    -0.62
    VIRONMENT
    -0.61
     fiscal
    -0.56
    nage
    -0.52
    modèle
    -0.52
    ieri
    -0.52
    yorsunuz
    -0.51
    UMNS
    -0.51
    toFloat
    -0.50
    POSITIVE LOGITS
     дописавши
    0.87
    ThroughAttribute
    0.85
    ConstraintMaker
    0.84
    TintMode
    0.80
    kháu
    0.79
    StructEnd
    0.73
    Personendaten
    0.71
    :✨
    0.71
    oa̍t
    0.70
     ModelExpression
    0.69
    Activations Density 0.057%

    No Known Activations