© 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. 45617
    Prev
    Next
    INDEX
    Explanations

    little

    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
    little
    -2.70
     little
    -2.69
    Little
    -2.31
     Little
    -2.06
     LITTLE
    -2.03
    LITTLE
    -1.70
     lil
    -1.36
     poco
    -1.30
     pouco
    -1.29
     liten
    -1.23
    POSITIVE LOGITS
     مشين
    0.70
     cherchés
    0.63
    QMetaType
    0.57
    enumi
    0.57
    DeleteBehavior
    0.56
     فريبيس
    0.56
    EndContext
    0.51
    brainly
    0.51
    extAlignment
    0.50
    TagHelper
    0.49
    Activations Density 0.061%

    No Known Activations