© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78007
    Prev
    Next
    INDEX
    Explanations

    Simon/Sam

    np_max-act-logits · 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
    Negative Logits
     [](
    -0.58
     conscience
    -0.58
     parson
    -0.57
     Pyramids
    -0.56
     discriminator
    -0.55
     pyramids
    -0.55
     piety
    -0.55
    HtmlAttribute
    -0.53
     profits
    -0.53
     profit
    -0.53
    POSITIVE LOGITS
     EconPapers
    0.54
    ьаж
    0.50
    FunctionFlags
    0.50
    TagHelper
    0.48
    MENAFN
    0.47
     Mendes
    0.47
     zone
    0.47
    eventbus
    0.45
     Zone
    0.44
    mbic
    0.44
    Activations Density 0.003%

    No Known Activations