© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76034
    Prev
    Next
    INDEX
    Explanations

    Titles and excerpts

    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
     cutting
    -1.11
     chop
    -1.08
    cutting
    -1.04
     sawing
    -1.04
     Cutting
    -1.03
     chopping
    -1.03
     cutter
    -1.02
     cut
    -1.02
     cuts
    -1.00
     cutters
    -1.00
    POSITIVE LOGITS
    ImageContext
    0.59
     impegno
    0.42
    poň
    0.41
     captar
    0.37
    quei
    0.37
     vägen
    0.36
     Bertie
    0.36
     déplacements
    0.35
    шибка
    0.34
    suke
    0.33
    Activations Density 0.000%

    No Known Activations