© 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. 14496
    Prev
    Next
    INDEX
    Explanations

    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
     hands
    -0.58
    hands
    -0.54
    lets
    -0.47
    dima
    -0.47
    hanna
    -0.45
    java
    -0.44
    립
    -0.43
    simp
    -0.43
     Hands
    -0.42
    wood
    -0.42
    POSITIVE LOGITS
     estekak
    1.04
     nahilalakip
    0.87
     cherchés
    0.86
    gameserver
    0.77
    Their
    0.71
     للمعارف
    0.70
    MessageOf
    0.70
    tagHelperRunner
    0.69
     HasFactory
    0.67
     AssemblyCulture
    0.66
    Activations Density 0.042%

    No Known Activations