© 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. 1-CLT-HP
    7. 13156
    Prev
    Next
    INDEX
    Explanations

    websites and users

    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
     feltro
    -0.44
     وأن
    -0.43
    liau
    -0.42
     MaterialApp
    -0.42
    assertIs
    -0.42
     possesso
    -0.41
     épis
    -0.41
    質な
    -0.40
     ngờ
    -0.40
    ิลปะ
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    IntoConstraints
    0.70
    nocache
    0.63
    styleType
    0.62
     بيها
    0.61
    XmlRootElement
    0.60
    itinéraire
    0.60
    AddTagHelper
    0.59
     saites
    0.57
     kasarigan
    0.56
    Activations Density 0.014%

    No Known Activations