© 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. 5-CLT-HP
    7. 460
    Prev
    Next
    INDEX
    Explanations

    Proper nouns in article starts

    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
    ậc
    -0.52
    μβρίου
    -0.50
    ietf
    -0.48
    Etc
    -0.46
    geen
    -0.44
    ιού
    -0.43
    myself
    -0.43
    醐
    -0.41
    ibrill
    -0.40
     proprement
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.66
     kasarigan
    0.65
     surla
    0.64
     autorytatywna
    0.62
    IUrlHelper
    0.59
    expandindo
    0.59
     <",
    0.57
     <=",
    0.56
     AspNetCore
    0.56
     Paglinawan
    0.56
    Activations Density 0.602%

    No Known Activations