© 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. 5-CLT-HP
    7. 6059
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    Искәрмәләр
    -0.68
    ագրություններ
    -0.66
     Agronomy
    -0.63
     للمعارف
    -0.60
    يميديا
    -0.59
     שוליים
    -0.59
    rawDesc
    -0.55
    styleType
    -0.55
    Bibliographie
    -0.52
     '\\;'
    -0.51
    POSITIVE LOGITS
    FXML
    0.56
    inguém
    0.49
     Ведь
    0.47
    esModule
    0.47
     cime
    0.45
     Keluarga
    0.44
     چک
    0.44
     Mandalorian
    0.44
     נס
    0.44
    ✭✭
    0.43
    Activations Density 0.001%

    No Known Activations