© 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. 1-CLT-HP
    7. 9563
    Prev
    Next
    INDEX
    Explanations

    -logy

    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
    abestanden
    -0.59
     ویکی‌پدی
    -0.49
    ری
    -0.49
     Савезне
    -0.47
    ev
    -0.47
     cherchés
    -0.46
    MessageTagHelper
    -0.45
     진
    -0.45
    ology
    -0.44
    demi
    -0.43
    POSITIVE LOGITS
    InputBorder
    0.61
     Majefty
    0.60
     itſelf
    0.58
     ProtoMessage
    0.57
    principalTable
    0.55
     typelib
    0.55
     lyrics
    0.54
    getMinutes
    0.53
     Jefus
    0.53
    aryen
    0.53
    Activations Density 0.016%

    No Known Activations