© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45365
    Prev
    Next
    INDEX
    Explanations

    press

    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
     pressed
    -2.02
     press
    -2.00
     presses
    -1.97
     pressing
    -1.91
    pressing
    -1.84
    pressed
    -1.83
    Press
    -1.78
    press
    -1.77
     Pressing
    -1.75
     Pressed
    -1.75
    POSITIVE LOGITS
     Regel
    0.49
     y
    0.47
    شهاد
    0.47
    WAR
    0.46
     جان
    0.46
    ()
    0.46
     alap
    0.45
    懂
    0.45
     Mater
    0.45
    Factor
    0.44
    Activations Density 0.189%

    No Known Activations