© 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. 1-CLT-HP
    7. 11971
    Prev
    Next
    INDEX
    Explanations

    ceae

    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
    ceae
    -1.55
    ceous
    -0.64
    PreferredItem
    -0.54
    posedge
    -0.50
    tera
    -0.50
    ara
    -0.48
    ArrowToggle
    -0.45
    voter
    -0.45
    moveToFirst
    -0.42
    vote
    -0.41
    POSITIVE LOGITS
    contentLoaded
    0.65
    WindowConstants
    0.62
     kasarigan
    0.62
     itſelf
    0.59
     externi
    0.59
     Bernd
    0.58
    IUrlHelper
    0.58
     ragaz
    0.56
    inns
    0.56
     Lumpur
    0.55
    Activations Density 0.026%

    No Known Activations