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. 12815
    Prev
    Next
    INDEX
    Explanations

    other

    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
     resourceCulture
    -0.78
    Sortie
    -0.71
    MLLoader
    -0.71
     blessés
    -0.66
     InputDecoration
    -0.60
    migrationBuilder
    -0.60
     مرئيه
    -0.60
    struzione
    -0.58
    UrlResolution
    -0.58
     défis
    -0.57
    POSITIVE LOGITS
    principalTable
    0.49
     bindings
    0.49
     disambiguazione
    0.47
    ItemGroup
    0.46
    </tfoot>
    0.44
     bilateral
    0.44
    ující
    0.44
     geopolitical
    0.44
     proprie
    0.43
    SBATCH
    0.43
    Activations Density 0.007%

    No Known Activations