© 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. 0-CLT-HP
    7. 94757
    Prev
    Next
    INDEX
    Explanations

    excavation

    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
     excavation
    -2.19
     excavations
    -1.95
     Excavation
    -1.95
     excavated
    -1.86
    exca
    -1.81
     exca
    -1.73
    Exca
    -1.71
     Exca
    -1.58
     excav
    -1.27
     excavator
    -1.15
    POSITIVE LOGITS
    s
    0.59
    en
    0.50
    es
    0.49
    sus
    0.48
    sen
    0.48
    ⓘ
    0.48
    ,
    0.47
     Bold
    0.47
     for
    0.47
    smo
    0.45
    Activations Density 0.172%

    No Known Activations