© 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. 3520
    Prev
    Next
    INDEX
    Explanations

    Weiz

    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
    MigrationBuilder
    -0.57
     resourceCulture
    -0.57
    逅
    -0.54
    tagHelperRunner
    -0.49
     Browne
    -0.49
    busters
    -0.49
    assume
    -0.48
    KEYCODE
    -0.48
    msgTypes
    -0.48
     typename
    -0.48
    POSITIVE LOGITS
    الحياه
    0.59
    kháu
    0.58
    Демографія
    0.56
    RTLD
    0.54
    ēc
    0.54
     élections
    0.52
    TagMode
    0.52
     Wikimedijinoj
    0.51
    WarningLevel
    0.48
    ništvo
    0.48
    Activations Density 0.000%

    No Known Activations