© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72616
    Prev
    Next
    INDEX
    Explanations

    buildings

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     Buildings
    -0.83
    Buildings
    -0.74
     BoxDecoration
    -0.74
     architectures
    -0.73
     Construction
    -0.73
     BUILDINGS
    -0.73
    buildings
    -0.70
     constructions
    -0.70
     constructs
    -0.69
     buildings
    -0.68
    POSITIVE LOGITS
     house
    0.63
     home
    0.57
     palace
    0.51
     cathedral
    0.50
     church
    0.50
     bridge
    0.48
     chapel
    0.48
     temple
    0.46
     stu
    0.45
     dam
    0.45
    Activations Density 0.001%

    No Known Activations