© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42054
    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
    -1.66
     screening
    -1.61
    Screening
    -1.61
    screening
    -1.61
     screened
    -1.52
     screenings
    -1.20
     SCREEN
    -1.13
     Carolina
    -1.12
     Screen
    -1.05
    Screen
    -0.97
    POSITIVE LOGITS
    MarshalTo
    0.59
     cannons
    0.53
    ney
    0.53
     Emig
    0.52
     ویکی‌پدیا
    0.50
     Recipro
    0.50
    ResultSet
    0.48
     Succ
    0.48
     Death
    0.47
     followed
    0.47
    Activations Density 0.103%

    No Known Activations