© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    incidence

    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
     incidence
    -0.92
     Teachers
    -0.88
    incidence
    -0.85
    Teachers
    -0.79
    Teacher
    -0.78
     Teacher
    -0.77
    range
    -0.76
     Incidence
    -0.75
     range
    -0.75
     Educators
    -0.69
    POSITIVE LOGITS
    BeginContext
    0.57
     utafiti
    0.55
    EDEFAULT
    0.54
    этому
    0.46
     legacies
    0.46
    Overrides
    0.46
    <bos>
    0.45
     '.';
    0.45
     clays
    0.44
    smarty
    0.43
    Activations Density 0.198%

    No Known Activations