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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46076
    Prev
    Next
    INDEX
    Explanations

    SOD

    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
     sod
    -1.20
     Sod
    -1.02
    Sod
    -0.94
    sod
    -0.93
     SOD
    -0.48
    
    -0.47
    Berikut
    -0.47
    ELAND
    -0.46
    SOD
    -0.46
    chy
    -0.46
    POSITIVE LOGITS
    providedIn
    0.60
     незавершена
    0.60
     ब्रेकडाउन
    0.59
    expandindo
    0.59
    MeasureSpec
    0.57
     للاسماء
    0.56
     Roskov
    0.56
    ScopeManager
    0.55
    garage
    0.54
    NameInMap
    0.52
    Activations Density 0.629%

    No Known Activations