© 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. 38763
    Prev
    Next
    INDEX
    Explanations

    puzzle

    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
    ans
    -1.75
     puzzle
    -1.51
     Puzzle
    -1.42
    ANS
    -1.34
     puzzles
    -1.31
    Puzzle
    -1.18
    puzzle
    -1.13
     Puzzles
    -1.11
     ans
    -1.04
    anser
    -0.85
    POSITIVE LOGITS
     noires
    0.73
     ferdig
    0.65
    o
    0.63
     sää
    0.59
     ouvertes
    0.56
     démocr
    0.55
     hjemme
    0.54
     financières
    0.54
     complémentaires
    0.53
     tapasztal
    0.53
    Activations Density 1.552%

    No Known Activations