© 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. 9094
    Prev
    Next
    INDEX
    Explanations

    mammals

    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
    
    -0.90
    ToBounds
    -0.82
    MethodManager
    -0.75
    Portail
    -0.74
    Portale
    -0.71
    VersionUID
    -0.70
     primates
    -0.69
     nifer
    -0.69
     оригіналу
    -0.69
     primate
    -0.69
    POSITIVE LOGITS
     sää
    0.39
    gusted
    0.37
     occupies
    0.36
     Schn
    0.35
    giène
    0.35
    vaded
    0.35
     visar
    0.35
     общей
    0.35
    ργα
    0.35
    IUrlHelper
    0.35
    Activations Density 0.012%

    No Known Activations