© 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. 0-CLT-HP
    7. 95769
    Prev
    Next
    INDEX
    Explanations

    Code and web requests

    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
     to
    -0.54
     Fides
    -0.50
    dey
    -0.48
    ⋙
    -0.48
     den
    -0.46
     Currie
    -0.46
     conto
    -0.44
    EndContext
    -0.44
     gospodar
    -0.44
     Deniz
    -0.44
    POSITIVE LOGITS
    AlterField
    0.69
     autorytatywna
    0.68
    ChildScrollView
    0.67
     resourceCulture
    0.66
     indisponible
    0.64
    fromnode
    0.63
    abestanden
    0.63
     myſelf
    0.63
     viewDidLoad
    0.62
     كومونز
    0.61
    Activations Density 0.460%

    No Known Activations