© 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. 20-CLT-HP
    7. 77930
    Prev
    Next
    INDEX
    Explanations

    mid

    np_max-act-logits · 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
    PageContext
    -0.62
     ujednoznacz
    -0.61
     kasarigan
    -0.61
    ArgumentParser
    -0.54
     hoop
    -0.52
    uelos
    -0.51
     EconPapers
    -0.50
    IUrlHelper
    -0.49
    dings
    -0.48
     Vaux
    -0.48
    POSITIVE LOGITS
     للاسماء
    0.59
     estekak
    0.59
    copg
    0.56
    Diweddarwch
    0.53
     الحره
    0.52
    CERT
    0.49
     
    0.47
    west
    0.47
     otomatig
    0.46
     microm
    0.45
    Activations Density 0.001%

    No Known Activations