Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40854
    Prev
    Next
    INDEX
    Explanations

    TOP

    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
    ing
    -0.66
    ings
    -0.63
    TO
    -0.62
    TOS
    -0.56
    intro
    -0.55
    ring
    -0.54
    age
    -0.52
    adays
    -0.52
    tos
    -0.51
    alls
    -0.49
    POSITIVE LOGITS
    StoryboardSegue
    0.76
    帖最后由
    0.69
    ConstraintMaker
    0.68
    出版年
    0.65
    Shots
    0.64
    enumi
    0.63
    webElementXpaths
    0.63
    shund
    0.61
    +#+#
    0.61
    MLLoader
    0.60
    Activations Density 0.212%

    No Known Activations