© 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. 0-CLT-HP
    7. 43841
    Prev
    Next
    INDEX
    Explanations

    Code/text snippets

    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
     NgModule
    -0.77
    MemoryWarning
    -0.64
    BURGH
    -0.60
    typeorm
    -0.58
    Vidite
    -0.56
    semibold
    -0.56
    didReceive
    -0.56
     sad
    -0.55
    titial
    -0.55
     Réponses
    -0.54
    POSITIVE LOGITS
     referenties
    0.52
    othed
    0.52
    ion
    0.51
    Zacks
    0.50
    quisition
    0.50
     creș
    0.50
    os
    0.50
    izes
    0.50
     <=",
    0.49
    amélioration
    0.49
    Activations Density 0.735%

    No Known Activations