© 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. 0-CLT-HP
    7. 43132
    Prev
    Next
    INDEX
    Explanations

    legs

    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
     feet
    -2.34
     Feet
    -2.09
     legs
    -1.96
    feet
    -1.95
    Feet
    -1.74
     FEET
    -1.70
    legs
    -1.50
     Legs
    -1.48
    Legs
    -1.21
     Füße
    -1.18
    POSITIVE LOGITS
    pexpr
    0.61
    AllowUser
    0.58
     DET
    0.51
     dAtA
    0.51
    ftest
    0.50
     dis
    0.50
    />";
    0.49
    :"-"`
    0.48
    chern
    0.47
     jScrollPane
    0.47
    Activations Density 0.626%

    No Known Activations