© 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. 38809
    Prev
    Next
    INDEX
    Explanations

    cov

    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
    cov
    -1.67
     cov
    -0.82
    Cov
    -0.67
     covered
    -0.66
    Cover
    -0.63
    覆盖
    -0.61
    mallow
    -0.61
     covers
    -0.60
    Covered
    -0.60
     Cover
    -0.58
    POSITIVE LOGITS
    WriteBarrier
    0.60
    AddTagHelper
    0.59
    ///</
    0.56
    íncia
    0.55
     '\\;'
    0.49
    abestanden
    0.48
    Hentet
    0.46
    Geplaatst
    0.46
     Reverso
    0.44
    CodeAttribute
    0.44
    Activations Density 1.497%

    No Known Activations