© 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. 94406
    Prev
    Next
    INDEX
    Explanations

    motorcycles and naval

    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
     militaires
    -1.22
    AddTagHelper
    -1.16
     réguli
    -1.11
    AndEndTag
    -1.09
     fermés
    -1.06
     prêtres
    -1.00
     commerciales
    -0.98
     lèvres
    -0.98
     démocr
    -0.97
     genoux
    -0.97
    POSITIVE LOGITS
    ized
    0.54
     tra
    0.52
     tem
    0.50
     cal
    0.50
     sk
    0.49
     division
    0.49
     acc
    0.48
     con
    0.47
    ’
    0.47
     la
    0.46
    Activations Density 1.550%

    No Known Activations