© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    Names and Locations

    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
    otides
    -0.45
     webdriver
    -0.44
    hops
    -0.44
    dities
    -0.44
    QUES
    -0.44
    MENAFN
    -0.44
    eaway
    -0.43
    jścia
    -0.43
    forName
    -0.43
    NETT
    -0.43
    POSITIVE LOGITS
    mybatisplus
    0.62
    RenderAtEndOf
    0.62
     NSCoder
    0.61
     المعيارى
    0.60
    LabelTagHelper
    0.57
    contentLoaded
    0.56
    WillAppear
    0.56
    :✨
    0.54
     članak
    0.54
    Portale
    0.54
    Activations Density 0.005%

    No Known Activations