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. 74269
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     artistique
    -0.72
     artistic
    -0.66
    InjectAttribute
    -0.65
     nahilalakip
    -0.64
     ARTS
    -0.63
     sztuki
    -0.63
     artis
    -0.63
     Arts
    -0.62
     künstler
    -0.62
     Artist
    -0.61
    POSITIVE LOGITS
     cout
    0.62
    illust
    0.60
     pup
    0.57
    opardy
    0.56
     interior
    0.56
     flor
    0.55
     pot
    0.55
     typo
    0.55
     cel
    0.53
     Interior
    0.52
    Activations Density 0.084%

    No Known Activations