© 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. 9158
    Prev
    Next
    INDEX
    Explanations

    screening

    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
     Screening
    -0.85
     screening
    -0.80
     screen
    -0.75
     screened
    -0.73
    screen
    -0.72
    Screening
    -0.70
    screening
    -0.69
     Screen
    -0.69
     Screens
    -0.67
     SCREEN
    -0.65
    POSITIVE LOGITS
    Personendaten
    0.79
    SharedCtor
    0.61
     Normdatei
    0.60
    مزید
    0.59
    maru
    0.58
     martyrs
    0.54
    paramref
    0.54
    ÊNCIAS
    0.54
    TagHelper
    0.54
    athlon
    0.54
    Activations Density 0.130%

    No Known Activations