© 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. 77980
    Prev
    Next
    INDEX
    Explanations

    random text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.66
     Vikipedi
    -0.62
     StringVar
    -0.58
    readFileSync
    -0.57
    heça
    -0.57
    참고
    -0.56
    {?>
    -0.54
    맑
    -0.53
    Slap
    -0.53
    GroupLayout
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.54
    posób
    0.48
     tour
    0.47
    jahtera
    0.42
     sebagai
    0.42
    المكان
    0.42
    SuccessListener
    0.41
     host
    0.41
    idopsis
    0.40
     szóci
    0.39
    Activations Density 0.001%

    No Known Activations