© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    geography and water

    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
    GraphicsUnit
    -0.57
     olvides
    -0.52
    Portale
    -0.52
    ScopeManager
    -0.52
     autorytatywna
    -0.52
    quelles
    -0.50
     gesloten
    -0.49
    AutoScale
    -0.49
     ő
    -0.48
    ParallelGroup
    -0.48
    POSITIVE LOGITS
    TypedDataSet
    0.60
     Diſ
    0.57
     myſelf
    0.55
     Eſ
    0.54
     propOrder
    0.54
     himſelf
    0.54
    PRNewswire
    0.53
     Monfieur
    0.52
     himo
    0.52
    معلومات
    0.51
    Activations Density 0.021%

    No Known Activations