Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74204
    Prev
    Next
    INDEX
    Explanations

    Indians

    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
     jspb
    -0.63
    MigrationBuilder
    -0.58
     parvenir
    -0.56
    __(/*!
    -0.54
    SHO
    -0.54
     disambiguazione
    -0.51
     gardes
    -0.51
    ngOn
    -0.51
    cse
    -0.50
     habe
    -0.50
    POSITIVE LOGITS
     winds
    0.72
     concludes
    0.70
     concluded
    0.70
     wrapped
    0.68
     conclude
    0.67
     wind
    0.66
     conven
    0.66
     wraps
    0.65
     recon
    0.65
     enters
    0.63
    Activations Density 0.001%

    No Known Activations