© 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. 4-CLT-HP
    7. 11
    Prev
    Next
    INDEX
    Explanations

    ankles/ankle injuries

    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
    StoryboardSegue
    -0.54
    testng
    -0.50
     فريبيس
    -0.49
    removed
    -0.47
     vak
    -0.46
    sink
    -0.45
    хьтан
    -0.45
     unknownFields
    -0.45
     parseFrom
    -0.45
     useAppContext
    -0.45
    POSITIVE LOGITS
    ьаж
    0.66
    bra
    0.65
    :✨
    0.64
     bracelets
    0.63
     bracelet
    0.61
    луй
    0.58
    Bra
    0.57
     Braga
    0.57
    ButterKnife
    0.56
    saraba
    0.56
    Activations Density 0.001%

    No Known Activations