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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14182
    Prev
    Next
    INDEX
    Explanations

    the word "of" and words associated with categorization or citation.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     disambiguazione
    -0.91
     ErrIntOverflow
    -0.78
     étoit
    -0.69
     âgé
    -0.69
     évêque
    -0.68
     mourut
    -0.68
     mourir
    -0.65
     pouvoit
    -0.65
    titleMargin
    -0.64
     ब्रेकडाउन
    -0.63
    POSITIVE LOGITS
    <bos>
    0.78
     Wicidata
    0.49
     
    0.48
    [
    0.47
    .
    0.47
    ",
    0.47
    (
    0.47
    addGap
    0.46
    ',
    0.46
    parametrize
    0.44
    Activations Density 0.561%

    No Known Activations