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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1587
    Prev
    Next
    INDEX
    Explanations

    foods that are served with other foods

    oai_token-act-pair · gemini-2.0-flash

    food dishes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     internetowa
    -0.46
     AspNetCore
    -0.45
    parsedMessage
    -0.42
     createStore
    -0.42
     OkHttpClient
    -0.42
     sério
    -0.41
    BagLayout
    -0.41
     dressing
    -0.41
    InjectAttribute
    -0.41
    ĩnh
    -0.40
    POSITIVE LOGITS
    DeleteBehavior
    0.68
     facie
    0.62
    MigrationBuilder
    0.60
    mobileqq
    0.54
    SwingConstants
    0.54
    مقاله
    0.54
    </tfoot>
    0.53
    AllowAnonymous
    0.53
     Tull
    0.53
     Aguas
    0.53
    Activations Density 1.602%

    No Known Activations