© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38971
    Prev
    Next
    INDEX
    Explanations

    documents

    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
     NSCoder
    -0.84
    DoubleQuotes
    -0.75
     Trow
    -0.64
    بوابة
    -0.62
    AddTagHelper
    -0.60
    jeune
    -0.60
    IntoConstraints
    -0.60
    quipe
    -0.60
     Match
    -0.60
    porre
    -0.60
    POSITIVE LOGITS
    saraba
    0.54
    <bos>
    0.46
     “
    0.43
     ngan
    0.42
    rxjs
    0.41
    cés
    0.41
    IRQn
    0.41
    EventArgs
    0.41
    cées
    0.41
     getApp
    0.40
    Activations Density 1.652%

    No Known Activations