© 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. 8633
    Prev
    Next
    INDEX
    Explanations

    building

    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
     buildings
    -1.00
     building
    -0.95
    buildings
    -0.88
     Building
    -0.79
    Building
    -0.74
    building
    -0.72
     BUILDING
    -0.72
     Buildings
    -0.65
    Buildings
    -0.65
     BUILDINGS
    -0.64
    POSITIVE LOGITS
     princí
    0.54
     vectorielle
    0.52
     provisoire
    0.52
     spørgsmål
    0.52
     anyag
    0.52
    Hentet
    0.51
     հղումներ
    0.50
    
    0.50
     convaincre
    0.50
     forcé
    0.50
    Activations Density 0.059%

    No Known Activations