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. 40801
    Prev
    Next
    INDEX
    Explanations

    configure

    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
     للمعارف
    -0.77
    jgl
    -0.61
     internetowa
    -0.59
     configure
    -0.59
    <?
    -0.56
    clerview
    -0.55
    PYX
    -0.54
    ChildScrollView
    -0.53
     raiſ
    -0.53
     bağlantılar
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.58
    l
    0.55
    y
    0.52
    es
    0.50
    ton
    0.49
    t
    0.49
     Point
    0.49
    r
    0.48
    tagHelperRunner
    0.48
     censiti
    0.47
    Activations Density 0.205%

    No Known Activations