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. 1-CLT-HP
    4. 12846
    Prev
    Next
    INDEX
    Explanations

    eng

    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
     Bard
    -1.52
    Bard
    -1.26
     bard
    -1.12
     للاسماء
    -0.61
    hyrchwyd
    -0.60
    سطس
    -0.58
    "]));
    -0.56
     الرخصة
    -0.55
    :+:
    -0.54
    ViewChild
    -0.53
    POSITIVE LOGITS
    ic
    0.60
     CreateTagHelper
    0.59
    iche
    0.53
     IC
    0.51
    OCC
    0.49
    sour
    0.49
     Beecher
    0.49
    acterium
    0.49
    bindingNavigator
    0.48
    achu
    0.47
    Activations Density 0.009%

    No Known Activations