© 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. 15485
    Prev
    Next
    INDEX
    Explanations

    screen

    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
     screen
    -1.35
    screen
    -1.17
    Screen
    -1.09
     Screen
    -1.09
     screens
    -0.94
     SCREEN
    -0.90
     screening
    -0.86
    SCREEN
    -0.83
     screened
    -0.82
     Screens
    -0.81
    POSITIVE LOGITS
    IVEREF
    0.69
    
    0.65
    تقاوى
    0.60
     Houſe
    0.59
    fvar
    0.58
     LEYENDO
    0.57
    expandindo
    0.57
    ẹo
    0.56
    principalColumn
    0.56
    ừ
    0.56
    Activations Density 0.009%

    No Known Activations