© 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. 20-CLT-HP
    7. 76661
    Prev
    Next
    INDEX
    Explanations

    medical procedures and locations

    np_max-act-logits · 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
    +#+#
    -0.90
    цездатний
    -0.77
    yntaxException
    -0.70
     виправивши
    -0.70
    WithIOException
    -0.70
     disambiguazione
    -0.67
    queryInterface
    -0.66
    sidemargin
    -0.66
    initializeApp
    -0.66
    uxxxx
    -0.65
    POSITIVE LOGITS
    have
    0.45
     semblables
    0.43
    fgaben
    0.43
     have
    0.39
     dieux
    0.39
     Have
    0.39
     slutet
    0.38
     gemak
    0.37
    setChecked
    0.37
     lunghezza
    0.37
    Activations Density 0.001%

    No Known Activations