© 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. 94069
    Prev
    Next
    INDEX
    Explanations

    feet/body parts

    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
    مراجع
    -0.73
    NewLabel
    -0.73
     HttpNotFound
    -0.70
     LIABLE
    -0.69
    RectangleBorder
    -0.68
     PLAT
    -0.67
    VersionUID
    -0.67
    Atentamente
    -0.67
    ADRID
    -0.66
    VERTISEMENT
    -0.65
    POSITIVE LOGITS
     or
    0.51
    /
    0.39
    0.39
     vectorielle
    0.38
     bré
    0.37
    ↵↵
    0.36
     banget
    0.36
    قایناق‌لار
    0.35
    </strong>
    0.35
    belline
    0.34
    Activations Density 0.010%
    No Known Activations