© 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. 20-CLT-HP
    7. 71320
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     kasarigan
    -0.57
     ExecuteAsync
    -0.55
     Defenders
    -0.54
    Diweddarwch
    -0.54
     negroes
    -0.53
     <=",
    -0.53
     Autorizaciones
    -0.51
    Ở
    -0.50
     Negroes
    -0.50
     marbre
    -0.50
    POSITIVE LOGITS
     Are
    0.75
     sī
    0.58
    Are
    0.58
    MatButtonModule
    0.52
     Aren
    0.52
    initializeApp
    0.51
    QObject
    0.49
    醐
    0.49
    WebVitals
    0.48
    MatIconModule
    0.48
    Activations Density 0.000%

    No Known Activations