© 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. 16043
    Prev
    Next
    INDEX
    Explanations

    suffixes

    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
    er
    -0.52
    actory
    -0.49
    anc
    -0.49
    as
    -0.47
    an
    -0.45
    erii
    -0.45
    aks
    -0.45
    ander
    -0.44
    estor
    -0.44
    anco
    -0.44
    POSITIVE LOGITS
    MessageTagHelper
    0.73
    initializeApp
    0.70
    Diwedd
    0.68
    GraphicsUnit
    0.66
     EconPapers
    0.64
    +#+#
    0.63
     autorytatywna
    0.62
    ,:);
    0.62
     الحره
    0.61
     Prose
    0.60
    Activations Density 0.011%

    No Known Activations