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. 16360
    Prev
    Next
    INDEX
    Explanations

    colloquial language related to sports scores and match outcomes

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
    simus
    -0.56
     wireType
    -0.51
    ","");
    -0.49
     civil
    -0.49
    undas
    -0.48
    tamin
    -0.48
     frot
    -0.47
     Suddenly
    -0.47
     Grie
    -0.46
    civil
    -0.46
    POSITIVE LOGITS
    SequentialGroup
    0.67
    afficheront
    0.67
    InjectAttribute
    0.62
    $_['
    0.58
     onCreateView
    0.53
    paksa
    0.52
     mostrarán
    0.52
    agliari
    0.52
    cault
    0.52
    ürnberg
    0.52
    Activations Density 1.212%

    No Known Activations