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. 16239
    Prev
    Next
    INDEX
    Explanations

    legal documents and information related to grievances

    oai_token-act-pair · gemini-2.0-flash

    mixed text and form notation

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

    official documents

    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
    -0.82
     متعلقه
    -0.70
    psack
    -0.70
     Majefty
    -0.70
    ReusableCell
    -0.69
    +:+
    -0.67
     kasarigan
    -0.67
     itſelf
    -0.66
     purpoſe
    -0.65
    ſelf
    -0.65
    POSITIVE LOGITS
    Välislingid
    0.52
    ళ
    0.45
    庁
    0.45
     Original
    0.43
     dele
    0.42
     Torn
    0.42
     plan
    0.41
     HttpNotFound
    0.40
    Original
    0.40
     original
    0.40
    Activations Density 1.512%

    No Known Activations