© 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. 16178
    Prev
    Next
    INDEX
    Explanations

    Please

    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
     esternos
    -0.63
    Personensuche
    -0.61
    Activité
    -0.58
     estekak
    -0.57
     Abp
    -0.54
    lorette
    -0.53
     />";
    -0.53
    AFN
    -0.52
     edili
    -0.52
     lenker
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.71
     invoke
    0.57
     simulate
    0.56
     run
    0.55
    enterOuterAlt
    0.52
     Commencez
    0.51
     seed
    0.50
     configure
    0.49
     ran
    0.49
    Ejec
    0.48
    Activations Density 0.030%

    No Known Activations