© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    :+:
    -0.57
     Chwiliwch
    -0.54
    AsUp
    -0.53
    latego
    -0.51
    principalTable
    -0.50
     Administrativna
    -0.50
    BrowserModule
    -0.49
     Shed
    -0.48
     ridges
    -0.47
     glaciers
    -0.45
    POSITIVE LOGITS
    corbic
    0.65
    BufferException
    0.57
     وتسجيلات
    0.57
     CURIAM
    0.56
     Wikispecies
    0.55
    GraphicsUnit
    0.54
    INCENT
    0.52
     الحره
    0.50
    imetric
    0.50
    bootstrapcdn
    0.49
    Activations Density 0.039%

    No Known Activations