© 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. 40957
    Prev
    Next
    INDEX
    Explanations

    events and revealing

    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
     exposed
    -1.10
     exposure
    -0.81
     Exposed
    -0.80
     raised
    -0.74
     exp
    -0.73
     expos
    -0.73
     EXPOSURE
    -0.71
     Exposure
    -0.70
    exposed
    -0.69
     expose
    -0.69
    POSITIVE LOGITS
     policiales
    0.62
     hebdomada
    0.59
     genoux
    0.59
     revanche
    0.59
     Grecs
    0.58
     enfans
    0.58
    WriteTagHelper
    0.57
     démocr
    0.56
     Conſ
    0.56
    openqa
    0.56
    Activations Density 0.114%

    No Known Activations