© 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. 38891
    Prev
    Next
    INDEX
    Explanations

    config files

    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
     "..\..\
    -0.79
     مشين
    -0.67
     deep
    -0.65
    ativement
    -0.65
    ))^{
    -0.58
     deeply
    -0.57
     Schmitt
    -0.57
     Jeffries
    -0.56
    bericht
    -0.56
    versa
    -0.55
    POSITIVE LOGITS
     auffi
    0.59
     myſelf
    0.57
    RegressionTest
    0.55
     Athenians
    0.54
     Majefty
    0.54
     Simplified
    0.54
     monog
    0.54
     Gallimard
    0.53
    낌
    0.53
     ſy
    0.52
    Activations Density 1.667%

    No Known Activations