© 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. 5-CLT-HP
    7. 1211
    Prev
    Next
    INDEX
    Explanations

    scientific models/analysis

    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
     ब्रेकडाउन
    -0.54
    OGND
    -0.43
    hängig
    -0.40
    ิว
    -0.39
     bet
    -0.39
     ej
    -0.38
     Argus
    -0.38
    PRF
    -0.38
     الرياضيه
    -0.38
    เภ
    -0.38
    POSITIVE LOGITS
    crollView
    0.65
    ModelAdmin
    0.60
    aronder
    0.57
    bootstrapcdn
    0.56
     ModelExpression
    0.55
    aarrggbb
    0.55
     thickening
    0.54
    SequentialGroup
    0.52
    acamata
    0.52
     ductile
    0.52
    Activations Density 0.001%

    No Known Activations