© 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. 16190
    Prev
    Next
    INDEX
    Explanations

    Rhe

    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
     correctement
    -0.49
     oídos
    -0.47
     promoção
    -0.47
     conoscenza
    -0.47
     promosi
    -0.47
     connaissance
    -0.46
     descrição
    -0.45
     conocimiento
    -0.44
     économiques
    -0.44
     correctamente
    -0.43
    POSITIVE LOGITS
    IsContent
    0.84
    awtextra
    0.83
    ArgsConstructor
    0.81
    AddTagHelper
    0.80
     Audiodateien
    0.80
     متعلقه
    0.79
    makeConstraints
    0.79
    NUMX
    0.77
    EDEFAULT
    0.75
    AxisAlignment
    0.73
    Activations Density 0.073%

    No Known Activations