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. 11182
    Prev
    Next
    INDEX
    Explanations

    and

    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
     synonyms
    -0.50
     fouls
    -0.48
     vectors
    -0.48
     polynomials
    -0.48
    ?,?,
    -0.48
     Nons
    -0.48
     vouchers
    -0.47
     averages
    -0.47
     factions
    -0.47
     knuckles
    -0.46
    POSITIVE LOGITS
     Réponses
    0.73
     autorytatywna
    0.69
    store
    0.66
     pinulongan
    0.66
     []:
    0.59
     محفوظة
    0.59
    script
    0.58
    shit
    0.57
    rest
    0.56
    shift
    0.56
    Activations Density 0.102%

    No Known Activations