© 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. 40741
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed"

    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
    cted
    -1.13
    beled
    -1.13
    aded
    -1.10
    duled
    -1.09
    ofed
    -1.09
    ulted
    -1.02
    didSet
    -0.99
    hematical
    -0.97
    emed
    -0.96
    resented
    -0.94
    POSITIVE LOGITS
    ly
    1.04
    ness
    0.97
    s
    0.76
    ci
    0.69
    no
    0.63
    ges
    0.63
    ni
    0.62
    ley
    0.61
    nya
    0.61
    ся
    0.61
    Activations Density 0.053%

    No Known Activations