© 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. 5-CLT-HP
    7. 91090
    Prev
    Next
    INDEX
    Explanations

    Locations and organizations

    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
    ContentLoaded
    -0.54
     getApp
    -0.53
     sherds
    -0.53
    ftagPool
    -0.52
    MessageTagHelper
    -0.51
    RRect
    -0.50
    invokeLater
    -0.49
    InstrumentedTest
    -0.49
     raiſ
    -0.49
     meant
    -0.49
    POSITIVE LOGITS
     government
    0.58
     gouvernements
    0.56
    government
    0.55
     gover
    0.54
     govern
    0.54
     governing
    0.53
    りする
    0.53
     Government
    0.53
    TagHelpers
    0.52
     gouvernement
    0.51
    Activations Density 0.002%

    No Known Activations