© 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. 90918
    Prev
    Next
    INDEX
    Explanations

    header

    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
    ServletConfig
    -0.53
    Conductor
    -0.52
     Bourgoin
    -0.51
     AssemblyTitle
    -0.50
     Theod
    -0.47
     onItemClick
    -0.46
     Conductor
    -0.46
     THEOD
    -0.46
    penup
    -0.46
    zone
    -0.46
    POSITIVE LOGITS
    ries
    0.62
    rey
    0.56
    ry
    0.52
    feira
    0.51
    pptx
    0.50
     gede
    0.49
     Gesù
    0.49
    rys
    0.49
    iek
    0.48
    fry
    0.47
    Activations Density 0.002%

    No Known Activations