© 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. 4-CLT-HP
    7. 3263
    Prev
    Next
    INDEX
    Explanations

    w

    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
     समीक्षक
    -0.60
     Réponses
    -0.57
    tellation
    -0.54
    transQ
    -0.53
    oi
    -0.53
    arr
    -0.52
    LayoutStyle
    -0.52
    arroll
    -0.52
    TG
    -0.51
    λιο
    -0.51
    POSITIVE LOGITS
    σμα
    0.55
    Parcelize
    0.50
    DIRECTIONS
    0.48
    enfance
    0.48
    WithIOException
    0.48
     nahilalakip
    0.47
     timed
    0.44
    WritableDatabase
    0.43
    Життєпис
    0.43
     scène
    0.42
    Activations Density 0.004%

    No Known Activations