© 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. 95379
    Prev
    Next
    INDEX
    Explanations

    stay

    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
     stayed
    -1.26
    stay
    -1.26
     stay
    -1.13
    Stay
    -1.06
     Stay
    -1.00
     staying
    -0.97
     STAY
    -0.91
    Staying
    -0.89
     Staying
    -0.89
     remained
    -0.82
    POSITIVE LOGITS
    Obrázky
    0.78
    contentLoaded
    0.72
    WebVitals
    0.72
     مرئيه
    0.70
     Вікіпе
    0.68
    CompleteListener
    0.66
    windowFixed
    0.65
    kloped
    0.64
    ineno
    0.63
     NSCoder
    0.63
    Activations Density 0.020%

    No Known Activations