© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13270
    Prev
    Next
    INDEX
    Explanations

    Eye protection

    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
     glasses
    -1.15
     goggles
    -1.09
     Glasses
    -1.06
     sunglasses
    -1.04
    glasses
    -1.03
     eyewear
    -0.99
     eyeglasses
    -0.97
    oggles
    -0.94
     spectacles
    -0.89
     Sunglasses
    -0.81
    POSITIVE LOGITS
     borne
    0.49
     drop
    0.48
    ecuted
    0.47
    drop
    0.47
    anches
    0.47
     Shore
    0.46
     take
    0.46
    Drop
    0.45
     Wood
    0.44
     perturb
    0.44
    Activations Density 0.013%

    No Known Activations