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. 20-CLT-HP
    4. 74015
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
     AssemblyVersion
    -0.68
     صوتيه
    -0.63
     Seeder
    -0.63
    ByVersion
    -0.61
     referenties
    -0.61
     EconPapers
    -0.61
    ագրություններ
    -0.59
    IVersion
    -0.58
    CppCodeGen
    -0.58
    EDEFAULT
    -0.58
    POSITIVE LOGITS
     bezeichneter
    0.50
    WEBPACK
    0.48
     entendu
    0.47
    DrawerToggle
    0.47
     trái
    0.44
    FOUND
    0.44
     eût
    0.44
    Història
    0.43
    +#+#
    0.43
    found
    0.43
    Activations Density 0.001%

    No Known Activations