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. 11125
    Prev
    Next
    INDEX
    Explanations

    this that

    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
     purpoſe
    -0.65
     reaſon
    -0.62
    ofday
    -0.59
    ckså
    -0.56
     edelstahl
    -0.56
    مقاله
    -0.56
    ніципалі
    -0.55
     ſtre
    -0.55
     ſche
    -0.54
     ImportError
    -0.52
    POSITIVE LOGITS
     Réponses
    0.60
    setVerticalGroup
    0.56
     comes
    0.54
    ExecuteReader
    0.53
    Parcelize
    0.52
     poch
    0.50
     stuff
    0.50
    PMailer
    0.49
    ,
    0.47
     deserves
    0.47
    Activations Density 0.081%

    No Known Activations