© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3889
    Prev
    Next
    INDEX
    Explanations

    all

    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
    antaranya
    -0.75
     للمعارف
    -0.73
     itſelf
    -0.65
    AnimationsModule
    -0.62
    NUMX
    -0.62
     continúas
    -0.61
    campista
    -0.61
     doubtnut
    -0.60
    itinéraire
    -0.60
    Amicalement
    -0.58
    POSITIVE LOGITS
     you
    0.57
     Meksiku
    0.52
     of
    0.48
    -
    0.47
     correctes
    0.46
    ost
    0.46
     modern
    0.46
     ویکی‌پدی
    0.45
     they
    0.44
     للاسماء
    0.43
    Activations Density 0.001%

    No Known Activations