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. 16240
    Prev
    Next
    INDEX
    Explanations

    names and words related to Chinese mythology and fantasy

    oai_token-act-pair · gemini-2.0-flash

    East Asian names/stories

    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
    Vidite
    -0.56
     StatelessWidget
    -0.44
     count
    -0.44
    count
    -0.44
    Ман
    -0.44
     heat
    -0.44
     freue
    -0.43
    熱
    -0.43
    ھو
    -0.43
     Wicidata
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.77
     Мексичка
    0.74
     الحره
    0.69
     فريبيس
    0.60
    brecht
    0.56
    tamide
    0.54
    Suerte
    0.54
     réessayer
    0.54
     offline
    0.54
     AspNetCore
    0.53
    Activations Density 1.666%

    No Known Activations