© 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. 16097
    Prev
    Next
    INDEX
    Explanations

    permanent

    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
     permanently
    -0.61
     permanent
    -0.56
     تانيه
    -0.56
    Чыганаклар
    -0.56
    TagMode
    -0.54
    بوابة
    -0.54
    تقاوى
    -0.52
     MenuView
    -0.52
    transQ
    -0.52
    ForValue
    -0.52
    POSITIVE LOGITS
    rawDesc
    0.56
     fallu
    0.55
    ValueGenerated
    0.54
    ejs
    0.51
     Polis
    0.50
     manqué
    0.49
    isto
    0.49
     XCTest
    0.48
    Tikang
    0.48
     letto
    0.47
    Activations Density 0.015%

    No Known Activations