Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16271
    Prev
    Next
    INDEX
    Explanations

    the word "president" and words that commonly precede it

    oai_token-act-pair · gemini-2.0-flash

    president of the

    np_token-act-pair-logits · gemini-2.0-flash

    president

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    Personensuche
    -0.72
     Houſe
    -0.62
     ویکی‌پدیای
    -0.59
     Chriftian
    -0.59
     Anſ
    -0.58
    isticated
    -0.56
    purl
    -0.56
     faſt
    -0.56
    AppService
    -0.56
     Monfieur
    -0.55
    POSITIVE LOGITS
    ソナ
    0.48
    Abitanti
    0.48
     يتيمه
    0.47
    سان
    0.44
     <=",
    0.44
     res
    0.42
    volta
    0.42
     Rueda
    0.41
     bolas
    0.41
     met
    0.41
    Activations Density 2.045%

    No Known Activations