© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1319
    Prev
    Next
    INDEX
    Explanations

    winter

    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
     winter
    -0.92
    —
    -0.72
     Winter
    -0.67
    ,
    -0.64
     ~
    -0.53
     −
    -0.52
     —
    -0.52
     WINTER
    -0.52
     fifty
    -0.50
    Winter
    -0.48
    POSITIVE LOGITS
    theless
    0.86
     مشين
    0.80
     للاسماء
    0.80
    teen
    0.78
     CreateTagHelper
    0.77
    存于互联网档案馆
    0.75
    adays
    0.75
     ویکی‌پدی
    0.74
     NSCoder
    0.74
    ever
    0.73
    Activations Density 0.021%

    No Known Activations