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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40034
    Prev
    Next
    INDEX
    Explanations

    arium/nery

    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
    arium
    -1.04
    nery
    -0.96
     Paglinawan
    -0.93
     كومونز
    -0.88
    kyard
    -0.79
     للاسماء
    -0.75
    annica
    -0.75
    chard
    -0.72
     ویکی‌پدیا
    -0.72
    amental
    -0.72
    POSITIVE LOGITS
    ofman
    0.54
    associations
    0.49
     sexes
    0.45
     imago
    0.44
    Sé
    0.43
     signin
    0.43
     chrétienne
    0.42
    e
    0.42
    DNN
    0.41
     Association
    0.41
    Activations Density 0.992%

    No Known Activations