© 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. 45718
    Prev
    Next
    INDEX
    Explanations

    do

    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
     Normdatei
    -0.68
    dirond
    -0.63
    mybatisplus
    -0.57
    Kariera
    -0.55
    ArrowToggle
    -0.54
     ivelany
    -0.53
    terscotch
    -0.52
    СТЬ
    -0.51
    lamabad
    -0.51
    FundMe
    -0.50
    POSITIVE LOGITS
    Capítulo
    0.56
    awtextra
    0.53
    $\
    0.52
    SHOT
    0.51
     Case
    0.49
    Shot
    0.49
     Shot
    0.49
    IntoConstraints
    0.48
     Solution
    0.48
     שוליים
    0.48
    Activations Density 0.006%

    No Known Activations