© 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. 6308
    Prev
    Next
    INDEX
    Explanations

    latest

    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
     InputDecoration
    -0.76
    DeleteBehavior
    -0.71
    SourceChecksum
    -0.71
     propOrder
    -0.69
    UnusedPrivate
    -0.68
    BeginContext
    -0.66
     initComponents
    -0.66
     resourceCulture
    -0.66
     насељу
    -0.65
     végétale
    -0.65
    POSITIVE LOGITS
     Industry
    0.52
    Industry
    0.51
     industry
    0.50
     up
    0.50
     emerging
    0.48
     going
    0.45
     so
    0.45
     Going
    0.42
    paar
    0.42
     existing
    0.41
    Activations Density 0.006%

    No Known Activations