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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94430
    Prev
    Next
    INDEX
    Explanations

    stressing

    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
    losis
    -1.01
    elsa
    -0.73
    bro
    -0.63
    br
    -0.53
     stressing
    -0.53
    bra
    -0.50
    tra
    -0.49
    spec
    -0.49
    tosa
    -0.48
    s
    -0.48
    POSITIVE LOGITS
     تضيفلها
    0.90
     Мексичка
    0.85
     فريبيس
    0.83
    Personensuche
    0.78
     ویکی‌پدیا
    0.77
    Šaltiniai
    0.75
     للاسماء
    0.75
     Taktlose
    0.74
     الرياضيه
    0.72
    abestanden
    0.70
    Activations Density 1.445%

    No Known Activations