© 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. 1-CLT-HP
    7. 8890
    Prev
    Next
    INDEX
    Explanations

    but

    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
     snippetHide
    -0.73
     للمعارف
    -0.70
    antlr
    -0.65
     invokingState
    -0.65
    ArrowToggle
    -0.65
    ​—
    -0.65
    tagHelperRunner
    -0.60
    BagLayout
    -0.59
    TagMode
    -0.59
    PMailer
    -0.57
    POSITIVE LOGITS
     voisins
    0.56
     proposées
    0.55
     state
    0.54
     européennes
    0.54
     alimentaires
    0.53
     vectorielles
    0.53
     estatales
    0.52
     élevées
    0.52
     cavalli
    0.50
    state
    0.50
    Activations Density 0.024%

    No Known Activations