© 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. 71517
    Prev
    Next
    INDEX
    Explanations

    Random info or code

    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
     NSCoder
    -0.81
    aarrggbb
    -0.73
     متعلقه
    -0.71
    rungsseite
    -0.69
    Rhestr
    -0.68
    ReusableCell
    -0.68
    MessageTagHelper
    -0.67
    featureID
    -0.64
    CardModule
    -0.64
     AssemblyCulture
    -0.63
    POSITIVE LOGITS
     Hype
    0.46
     Haj
    0.46
     jul
    0.45
    Haj
    0.44
    Published
    0.41
    שרה
    0.41
    EVAL
    0.40
    графия
    0.40
    typeparam
    0.39
    面の
    0.39
    Activations Density 0.000%

    No Known Activations