© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4588
    Prev
    Next
    INDEX
    Explanations

    eev

    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
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.66
     ſtate
    -0.62
     CreateTagHelper
    -0.61
    expandindo
    -0.61
    complexType
    -0.57
     ſte
    -0.57
     ſtre
    -0.57
     purpoſe
    -0.57
     houſe
    -0.56
     auffi
    -0.54
    POSITIVE LOGITS
     Gandhi
    0.73
    Gandhi
    0.55
     pygame
    0.54
    __);
    0.54
    #+#
    0.53
    gand
    0.52
     gand
    0.50
     estimés
    0.49
    arXiv
    0.48
    Tikang
    0.48
    Activations Density 0.000%

    No Known Activations