© 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. 44003
    Prev
    Next
    INDEX
    Explanations

    Light, silence or names

    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
     candle
    -1.71
     candles
    -1.52
     Candle
    -1.47
    Candle
    -1.25
     Candles
    -1.23
    candle
    -1.21
    Candles
    -1.09
    candles
    -0.98
     candlestick
    -0.94
     velas
    -0.86
    POSITIVE LOGITS
    fish
    0.69
    board
    0.67
    post
    0.65
    }{*}{
    0.65
    case
    0.65
    head
    0.61
    roll
    0.59
    block
    0.59
    able
    0.59
    box
    0.58
    Activations Density 0.071%

    No Known Activations