© 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. 92091
    Prev
    Next
    INDEX
    Explanations

    bundle

    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
     CreateTagHelper
    -0.81
    IntoConstraints
    -0.71
    帖最后由
    -0.65
     collaborazione
    -0.62
    +#+#
    -0.61
     bundle
    -0.60
     jöv
    -0.60
     oiseaux
    -0.60
     nemico
    -0.60
    pushFollow
    -0.60
    POSITIVE LOGITS
     points
    0.61
    ning
    0.60
    racy
    0.60
    ing
    0.60
     gri
    0.60
    uous
    0.59
    ating
    0.57
    leto
    0.56
    ous
    0.56
     er
    0.56
    Activations Density 1.679%

    No Known Activations