© 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. 4382
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    RegistryLite
    -0.88
    TypedDataSet
    -0.79
     EconPapers
    -0.78
     незавершена
    -0.71
     onCancelled
    -0.69
    IUrlHelper
    -0.66
    зулта
    -0.65
    RenderAtEndOf
    -0.65
    principalTable
    -0.64
    HtmlAttribute
    -0.63
    POSITIVE LOGITS
    bjs
    0.47
     doPost
    0.42
     partire
    0.41
    rus
    0.40
     elő
    0.40
     lanjut
    0.39
    icol
    0.39
    uelan
    0.39
     élas
    0.39
     cabello
    0.39
    Activations Density 0.006%

    No Known Activations