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. 74476
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    іга
    -0.59
    cided
    -0.55
    ccan
    -0.50
    gefunden
    -0.50
     taus
    -0.49
     spool
    -0.48
    foe
    -0.48
     taped
    -0.48
    logique
    -0.47
    ribune
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.76
     BaseActivity
    0.51
    apiVersion
    0.48
     idiom
    0.48
    ngày
    0.47
    Controllo
    0.46
    Pranala
    0.46
     BorderRadius
    0.45
     spec
    0.45
     ligiloj
    0.45
    Activations Density 0.009%

    No Known Activations