© 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. 1-CLT-HP
    7. 12344
    Prev
    Next
    INDEX
    Explanations

    integration

    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
    AndEndTag
    -0.60
    GEBURTSDATUM
    -0.56
    TagHelpers
    -0.56
     Biôgrafia
    -0.56
     utilisons
    -0.55
    :✨
    -0.55
    IUrlHelper
    -0.55
     AssemblyTitle
    -0.54
    новниш
    -0.52
    WebElementEntity
    -0.52
    POSITIVE LOGITS
    PyExc
    0.79
    awaiter
    0.53
     thrown
    0.52
    Ход
    0.52
    toJSONString
    0.52
    Примечания
    0.51
    帖最后由
    0.51
    Przypisy
    0.51
    /*
    0.50
     genie
    0.50
    Activations Density 0.009%

    No Known Activations