© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16095
    Prev
    Next
    INDEX
    Explanations

    headwear

    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
    Negative Logits
     pants
    -0.58
    LabelTagHelper
    -0.52
     trousers
    -0.52
     head
    -0.49
    rawDesc
    -0.48
     
    -0.48
    getDescriptor
    -0.48
     pant
    -0.46
     Head
    -0.45
     oil
    -0.45
    POSITIVE LOGITS
    UserScript
    0.80
     betweenstory
    0.77
    ंदीखरीदारी
    0.69
    IUrlHelper
    0.69
    TypedDataSet
    0.65
     meille
    0.65
    findpost
    0.64
     propOrder
    0.63
     varandra
    0.61
    følgelig
    0.60
    Activations Density 0.050%

    No Known Activations