© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1677
    Prev
    Next
    INDEX
    Explanations

    User, wear, woven

    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
     wear
    -1.45
     Wear
    -1.28
    User
    -1.20
     user
    -1.19
     User
    -1.10
    Wear
    -1.10
     WEAR
    -1.09
     worth
    -1.07
     wears
    -1.05
     worn
    -0.98
    POSITIVE LOGITS
    EndProject
    0.64
     bParam
    0.54
    ables
    0.53
     незавершена
    0.53
     Theſe
    0.53
    upol
    0.53
    cut
    0.52
    ness
    0.51
     chup
    0.51
    nehmen
    0.50
    Activations Density 0.089%

    No Known Activations