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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14089
    Prev
    Next
    INDEX
    Explanations

    a mix of Malay language words and references to food, family, and leisure activities

    oai_token-act-pair · gemini-2.0-flash

    Malay language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     fotográfico
    -0.62
    >";
    
    -0.61
     ")");
    -0.60
     grecque
    -0.59
     Protección
    -0.57
     lenker
    -0.57
    ConstraintMaker
    -0.57
    Personensuche
    -0.57
    ására
    -0.57
    fully
    -0.56
    POSITIVE LOGITS
    autoconfigure
    0.44
    TestingModule
    0.43
    rschein
    0.43
    pubs
    0.43
     ini
    0.43
     poco
    0.42
    PDOException
    0.42
     recevez
    0.42
    EditorBrowsable
    0.42
    ivoli
    0.42
    Activations Density 0.167%

    No Known Activations