Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44630
    Prev
    Next
    INDEX
    Explanations

    round

    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
     round
    -2.55
     Round
    -2.25
    Round
    -2.22
    round
    -2.09
     ROUND
    -2.09
     rounds
    -2.03
     rounded
    -1.88
     Rounds
    -1.80
    ROUND
    -1.77
    rounds
    -1.65
    POSITIVE LOGITS
    er
    0.79
    ingly
    0.69
    tled
    0.57
    ers
    0.57
    ER
    0.56
    ering
    0.55
     alt
    0.55
     Wayback
    0.55
    ered
    0.52
    tling
    0.52
    Activations Density 0.063%

    No Known Activations