© 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. 5-CLT-HP
    7. 6238
    Prev
    Next
    INDEX
    Explanations

    learn

    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
    Negative Logits
    FormTagHelper
    -0.73
     autorytatywna
    -0.72
    elemField
    -0.57
    istoitu
    -0.57
    Chham
    -0.57
    tagHelperRunner
    -0.54
    dafx
    -0.54
     conoscenza
    -0.54
     vectorielles
    -0.52
     Winaray
    -0.52
    POSITIVE LOGITS
     more
    0.61
    CppMethod
    0.58
     the
    0.56
     and
    0.53
     about
    0.49
     even
    0.49
    chern
    0.48
    /~
    0.46
    perror
    0.45
     &
    0.45
    Activations Density 0.001%

    No Known Activations