© 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. 72059
    Prev
    Next
    INDEX
    Explanations

    cutting/manufacturing

    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
    AndEndTag
    -0.94
     تعدى
    -0.67
    WithIOException
    -0.64
     propOrder
    -0.60
    mphony
    -0.59
    awtextra
    -0.55
     disponibilités
    -0.50
    іга
    -0.50
     متعلقه
    -0.50
    arrête
    -0.49
    POSITIVE LOGITS
     cut
    0.90
    cut
    0.74
     sa
    0.71
     cast
    0.67
     he
    0.65
     worked
    0.64
     milled
    0.62
     turned
    0.60
    cast
    0.60
     machine
    0.60
    Activations Density 0.001%

    No Known Activations