© 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. 78208
    Prev
    Next
    INDEX
    Explanations

    may

    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
    ArgsConstructor
    -0.68
    دانشنامهٔ
    -0.64
    OGND
    -0.57
    quelize
    -0.56
    kháu
    -0.55
    setupUi
    -0.53
     CURIAM
    -0.53
    faker
    -0.52
    apimachinery
    -0.52
    do
    -0.51
    POSITIVE LOGITS
     come
    0.86
     Come
    0.61
     comes
    0.57
     always
    0.54
    Come
    0.54
     COME
    0.52
    come
    0.50
    shmi
    0.49
     للاسماء
    0.48
    щин
    0.47
    Activations Density 0.001%

    No Known Activations