© 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. 16013
    Prev
    Next
    INDEX
    Explanations

    lain

    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
    ureusement
    -0.58
     disparu
    -0.55
     étoit
    -0.53
     fallu
    -0.52
    itrile
    -0.49
    etine
    -0.49
     damals
    -0.48
     pouvoit
    -0.48
     dAtA
    -0.48
     modernes
    -0.48
    POSITIVE LOGITS
     незавершена
    0.80
    ंदीखरीदारी
    0.67
     Италијани
    0.64
    Vidite
    0.61
    principalTable
    0.59
     CreateTagHelper
    0.59
    Життєпис
    0.59
    WillAppear
    0.57
    StreetMap
    0.56
     dynamite
    0.56
    Activations Density 0.007%

    No Known Activations