© 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. 10103
    Prev
    Next
    INDEX
    Explanations

    Royalty, surgery, medicine

    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
     Queen
    -0.77
    JspWriter
    -0.73
    Bienvenue
    -0.71
     queen
    -0.67
    Queen
    -0.66
    queen
    -0.64
    ]-->
    -0.63
    elemField
    -0.62
     QUEEN
    -0.62
    Ecotoxicity
    -0.61
    POSITIVE LOGITS
     intptr
    0.59
    an
    0.59
    ly
    0.50
    n
    0.50
     defaultstate
    0.49
    ie
    0.49
     StringTokenizer
    0.48
    ante
    0.48
    u
    0.48
    r
    0.47
    Activations Density 0.071%

    No Known Activations