© 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. 1082
    Prev
    Next
    INDEX
    Explanations

    research and education

    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
    таратура
    -0.64
    اریخ
    -0.64
    Tembelea
    -0.60
     nakalista
    -0.59
    Espèce
    -0.57
    Билгалдахарш
    -0.54
    sizeCache
    -0.53
    WebElementEntity
    -0.53
    UserScript
    -0.53
     Rukh
    -0.51
    POSITIVE LOGITS
    BASEPATH
    0.52
    ware
    0.49
     المعيارى
    0.47
    (!__
    0.46
     Area
    0.45
     AssemblyCulture
    0.45
    accepte
    0.44
    Area
    0.44
     banderas
    0.44
    жидан
    0.43
    Activations Density 0.001%

    No Known Activations