© 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. 4-CLT-HP
    7. 2992
    Prev
    Next
    INDEX
    Explanations

    adverbs and discourse markers

    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
    kuuta
    -0.53
     are
    -0.52
     starve
    -0.45
     visit
    -0.43
     nale
    -0.43
    TRIBUT
    -0.42
     relate
    -0.42
     converse
    -0.42
     imitate
    -0.42
     wieś
    -0.42
    POSITIVE LOGITS
     wants
    0.94
     publishes
    0.92
     sells
    0.88
     owns
    0.88
     recognizes
    0.86
     uses
    0.85
     considers
    0.82
     defines
    0.82
     chooses
    0.82
     refuses
    0.81
    Activations Density 0.018%

    No Known Activations