© 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. 43791
    Prev
    Next
    INDEX
    Explanations

    olig

    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
     reveal
    -0.63
    Photo
    -0.61
     guarantee
    -0.58
     Sociales
    -0.56
     buck
    -0.56
    ABAD
    -0.55
     expose
    -0.52
     esist
    -0.52
    Point
    -0.52
     anymore
    -0.52
    POSITIVE LOGITS
     disambiguazione
    0.70
    igator
    0.62
    astéroïdes
    0.57
     mxArray
    0.56
     WaitForSeconds
    0.56
    oplan
    0.55
    
    0.55
    enegger
    0.53
     calendriers
    0.53
     ilmiah
    0.53
    Activations Density 0.498%

    No Known Activations