© 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. 96141
    Prev
    Next
    INDEX
    Explanations

    Acronyms/Abbreviations

    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
    cookieParser
    -0.57
    shutil
    -0.56
    ScopeManager
    -0.54
    Scaler
    -0.52
    óngase
    -0.52
    CodeAttribute
    -0.51
    RUnlock
    -0.50
    archiviato
    -0.50
    addContainerGap
    -0.49
    Grath
    -0.48
    POSITIVE LOGITS
    BeginContext
    0.59
    UrlResolution
    0.57
    protoimpl
    0.54
    yev
    0.48
    Искәрмәләр
    0.48
    ValueStyle
    0.47
    出版年
    0.47
    сни
    0.46
    expandindo
    0.45
     المعيارى
    0.45
    Activations Density 0.002%

    No Known Activations