© 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. 11861
    Prev
    Next
    INDEX
    Explanations

    prom

    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
     prom
    -0.60
     Preparedness
    -0.54
    ente
    -0.52
    outines
    -0.52
    PointerException
    -0.51
    ovna
    -0.50
    ende
    -0.49
    ensä
    -0.49
    AddAttribute
    -0.49
     Avenue
    -0.48
    POSITIVE LOGITS
     estekak
    0.98
     وتسجيلات
    0.78
    kuuta
    0.66
    didSet
    0.63
     تضيفلها
    0.62
    رشف
    0.62
     XNUMX
    0.62
     Efq
    0.62
    فایل‌لار
    0.60
     كومونز
    0.60
    Activations Density 0.006%

    No Known Activations