© 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. 1-CLT-HP
    7. 15390
    Prev
    Next
    INDEX
    Explanations

    smooth

    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
     smooth
    -0.85
     smoothness
    -0.81
    smooth
    -0.72
     smoother
    -0.71
     Smooth
    -0.71
    Smooth
    -0.68
     SMO
    -0.56
     smoothly
    -0.52
     smoothed
    -0.50
     lisse
    -0.49
    POSITIVE LOGITS
    MarshalTo
    0.76
     فريبيس
    0.69
    \{\\
    0.67
    исленность
    0.62
    AndEndTag
    0.59
     الحره
    0.58
     ChromeDriver
    0.55
    GroupLayout
    0.54
    ESTAMP
    0.54
    Autoritní
    0.54
    Activations Density 0.059%

    No Known Activations