© 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. 0-CLT-HP
    7. 38519
    Prev
    Next
    INDEX
    Explanations

    conserved

    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
     Chwiliwch
    -0.83
    FunctionFlags
    -0.78
     Gazette
    -0.73
     EnglishChoose
    -0.73
    клопе
    -0.72
     мәкал
    -0.71
     /\.
    -0.71
    styleable
    -0.70
     geldig
    -0.69
     useAppContext
    -0.68
    POSITIVE LOGITS
     the
    0.56
    ttes
    0.52
     for
    0.50
    역
    0.49
    ----------------
    0.49
    ric
    0.47
    ________________
    0.47
    dores
    0.47
    ‌ی
    0.46
    ax
    0.44
    Activations Density 0.061%

    No Known Activations