© 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. 42776
    Prev
    Next
    INDEX
    Explanations

    exceeding limits

    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
     supérieures
    -0.90
     exceed
    -0.89
     pillar
    -0.87
    excellent
    -0.84
     exceeding
    -0.82
     chré
    -0.82
     excellente
    -0.80
     exceeds
    -0.79
     électroniques
    -0.79
     vectorielles
    -0.78
    POSITIVE LOGITS
     isInitialized
    0.52
     mut
    0.52
    als
    0.47
    AddTagHelper
    0.47
    ism
    0.47
     lomb
    0.45
     dep
    0.45
    tux
    0.44
     Wikip
    0.44
    enne
    0.44
    Activations Density 0.048%

    No Known Activations