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. 14164
    Prev
    Next
    INDEX
    Explanations

    the phrase "a lot"

    oai_token-act-pair · gemini-2.0-flash

    lot

    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
     ExecuteAsync
    -0.77
    Beaucoup
    -0.72
    EndInit
    -0.71
    Fordítás
    -0.68
    queryInterface
    -0.66
     doInBackground
    -0.65
     fufficient
    -0.64
     thiệu
    -0.63
    خواندن
    -0.63
    detectChanges
    -0.63
    POSITIVE LOGITS
     of
    0.74
    ########.
    0.66
    drž
    0.47
    romptu
    0.47
    живать
    0.46
    vité
    0.46
    oa̍t
    0.43
     pre
    0.41
     Preferencias
    0.41
    ies
    0.40
    Activations Density 0.722%

    No Known Activations