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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6007
    Prev
    Next
    INDEX
    Explanations

    words related to football

    oai_token-act-pair · gemini-2.0-flash

    words indicating utility

    np_token-act-pair-logits · gpt-4o-mini

    Sports context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    期刊论文
    -0.69
    NgModule
    -0.68
    LookAnd
    -0.67
    expandindo
    -0.67
     oprot
    -0.66
     NgModule
    -0.63
    awtextra
    -0.62
    HttpFoundation
    -0.62
    Referencie
    -0.60
    Diwedd
    -0.59
    POSITIVE LOGITS
     utility
    0.52
    setter
    0.52
    الإنجليزية
    0.50
     disambiguazione
    0.49
    entee
    0.43
    utility
    0.43
     free
    0.43
    torta
    0.42
    RENT
    0.41
    Utility
    0.41
    Activations Density 2.193%

    No Known Activations