Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16309
    Prev
    Next
    INDEX
    Explanations

    text discussing the role of mind and body

    oai_token-act-pair · gemini-2.0-flash

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betrekking
    -0.50
     Вікіпе
    -0.48
     ویکی‌پدیا
    -0.47
     büy
    -0.47
    Czytaj
    -0.46
     старости
    -0.46
    heets
    -0.45
    vol
    -0.45
    RUnlock
    -0.44
    VideoCapture
    -0.44
    POSITIVE LOGITS
     Roskov
    0.66
    脚注の使い方
    0.65
    CloseOperation
    0.63
    
    0.61
    migrationBuilder
    0.61
    GraphicsUnit
    0.61
    SBATCH
    0.59
    原始内容存档于
    0.56
    ControllerAdvice
    0.56
     Cataloging
    0.54
    Activations Density 0.564%

    No Known Activations