© 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. 39860
    Prev
    Next
    INDEX
    Explanations

    Winds

    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
     Winds
    -1.02
    Winds
    -0.86
    Wind
    -0.85
     estekak
    -0.83
     Wind
    -0.80
    winds
    -0.78
    WIND
    -0.70
     WIND
    -0.69
     wind
    -0.66
     minds
    -0.66
    POSITIVE LOGITS
    ized
    0.56
     Official
    0.53
    ัตว์
    0.49
    спубли
    0.48
    hatic
    0.48
     GeoNames
    0.48
    ofen
    0.48
     صوتيه
    0.48
    ropy
    0.47
    QMetaType
    0.46
    Activations Density 0.199%

    No Known Activations