© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3335
    Prev
    Next
    INDEX
    Explanations

    doctor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.57
    TypedDataSet
    -0.57
    Jeografia
    -0.55
    localctx
    -0.54
    日閲覧
    -0.48
    XmlAccessorType
    -0.48
    例文
    -0.47
     Braves
    -0.46
    .
    -0.45
     EClass
    -0.45
    POSITIVE LOGITS
     termica
    0.51
    äsident
    0.50
     bénévoles
    0.49
     huiles
    0.49
     puisse
    0.47
    Accessing
    0.47
     verrez
    0.47
     aš
    0.47
     líquida
    0.46
     mobilité
    0.46
    Activations Density 0.007%

    No Known Activations