© 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. 94607
    Prev
    Next
    INDEX
    Explanations

    physical locations/structures/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
     grounds
    -1.30
     doors
    -1.17
    doors
    -1.02
     hairs
    -1.02
     Grounds
    -1.01
    grounds
    -0.97
     itſelf
    -0.94
     gardens
    -0.93
     Jefus
    -0.90
     Efq
    -0.90
    POSITIVE LOGITS
     hi
    0.54
    hift
    0.48
    peed
    0.45
    ValueStyle
    0.45
     Mur
    0.44
     die
    0.43
    criptors
    0.43
     man
    0.42
     ap
    0.42
     or
    0.42
    Activations Density 0.294%

    No Known Activations