© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1910
    Prev
    Next
    INDEX
    Explanations

    of

    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
    dehyde
    -0.68
    libft
    -0.67
    المناصب
    -0.64
    gencies
    -0.62
    elfare
    -0.60
    redients
    -0.58
    allery
    -0.56
    ázaro
    -0.55
     cray
    -0.54
     חיצוניים
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.88
     بيها
    0.75
    InputBorder
    0.65
     touristique
    0.57
     passés
    0.57
     internationaux
    0.56
     passée
    0.54
    GEBURTSDATUM
    0.54
     dentaire
    0.54
     actrice
    0.52
    Activations Density 1.543%

    No Known Activations