© 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. 5-CLT-HP
    7. 94979
    Prev
    Next
    INDEX
    Explanations

    have

    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
    IUrlHelper
    -0.96
    InjectAttribute
    -0.93
    webElementXpaths
    -0.89
     ویکی‌پدیا
    -0.88
    новниш
    -0.86
    OGND
    -0.83
     ModelExpression
    -0.81
    IsContent
    -0.81
    principalColumn
    -0.79
     saites
    -0.78
    POSITIVE LOGITS
     to
    1.01
     difficulty
    0.69
     trouble
    0.66
     difficulties
    0.57
     little
    0.54
     decreased
    0.53
    trouble
    0.53
     no
    0.52
     reduced
    0.50
     lesser
    0.49
    Activations Density 0.001%

    No Known Activations