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. 11252
    Prev
    Next
    INDEX
    Explanations

    Research papers

    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
    مصادر
    -0.70
    FontOfSize
    -0.66
    ally
    -0.58
    ‬‬
    -0.58
    **********
    -0.54
    ‭
    -0.54
    nal
    -0.52
     portion
    -0.52
    mstyle
    -0.51
    abetes
    -0.51
    POSITIVE LOGITS
    :✨
    0.77
    niająca
    0.60
    findpost
    0.59
    InitVars
    0.56
    #
    0.53
    dymyr
    0.52
     dAtA
    0.52
    expandindo
    0.52
     дописавши
    0.50
    κτή
    0.50
    Activations Density 0.030%

    No Known Activations