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. 22-CLT-HP
    4. 74207
    Prev
    Next
    INDEX
    Explanations

    AT

    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
    ecake
    -0.60
     bağlantılar
    -0.55
     mergeFrom
    -0.54
    </caption>
    -0.54
    lehem
    -0.53
     biel
    -0.53
     WaitFor
    -0.53
     vinh
    -0.52
    Демографія
    -0.52
    γου
    -0.52
    POSITIVE LOGITS
    IsMutable
    0.55
     AssemblyProduct
    0.51
    Rohy
    0.50
     للاسماء
    0.49
    Assured
    0.47
     Neder
    0.46
    urlpatterns
    0.45
     Fiske
    0.44
     beginnetje
    0.44
     jScrollPane
    0.43
    Activations Density 0.004%

    No Known Activations