© 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. 1-CLT-HP
    7. 9643
    Prev
    Next
    INDEX
    Explanations

    roof

    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
    Not in Any Lists

    No Comments

    Negative Logits
     roof
    -1.08
    roof
    -0.99
     Roof
    -0.93
     ROOF
    -0.91
    Roof
    -0.86
     roofs
    -0.82
     ExecuteAsync
    -0.70
    expandindo
    -0.70
     roofing
    -0.69
    
    -0.69
    POSITIVE LOGITS
    errHandler
    0.62
    scape
    0.52
    ाप
    0.47
    less
    0.45
     domini
    0.44
    streams
    0.44
     of
    0.43
    tree
    0.43
    Less
    0.43
    ಠ
    0.42
    Activations Density 0.008%

    No Known Activations