© 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. 42619
    Prev
    Next
    INDEX
    Explanations

    pressure

    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
     pressure
    -2.27
    pressure
    -2.02
     Pressure
    -1.91
    Pressure
    -1.90
     PRESSURE
    -1.80
     pressures
    -1.61
     presión
    -1.48
     pressione
    -1.38
     pressured
    -1.38
     pression
    -1.34
    POSITIVE LOGITS
     /\.
    0.65
    TagMode
    0.65
     cigars
    0.63
    UIControlState
    0.61
     gills
    0.57
    DockStyle
    0.57
     skater
    0.56
    withIdentifier
    0.54
    الصفحه
    0.53
     groupBox
    0.53
    Activations Density 1.610%

    No Known Activations