© 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. 43159
    Prev
    Next
    INDEX
    Explanations

    treadmill

    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
     scorpion
    -0.76
     treadmill
    -0.64
     løpet
    -0.62
    amaño
    -0.59
    ("/:
    -0.58
    mişti
    -0.57
    kräf
    -0.56
    heute
    -0.56
    extAlignment
    -0.56
    graphicx
    -0.55
    POSITIVE LOGITS
    NOPQRST
    0.64
    stak
    0.55
    chrän
    0.54
    nen
    0.52
     Incompatible
    0.52
    
    0.52
    FixedSize
    0.51
     <=",
    0.50
    str
    0.49
    ned
    0.47
    Activations Density 0.054%

    No Known Activations