© 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-RES-MATRYOSHKA-DC
    7. 14804
    Prev
    Next
    INDEX
    Explanations

    the expression of enjoyment or fun

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    func
    -1.05
     Funny
    -0.93
     laughing
    -0.92
    Funny
    -0.90
     laugh
    -0.90
    FUN
    -0.87
     laughed
    -0.86
     enjoying
    -0.86
     enjoy
    -0.85
     Enjoy
    -0.85
    POSITIVE LOGITS
     fun
    1.30
    دانشنامهٔ
    0.79
     lenker
    0.71
     متحده
    0.68
     behulp
    0.68
     surla
    0.66
     ویکی‌پدیای
    0.65
     écoulé
    0.63
    AddTagHelper
    0.62
     ويكيميديا
    0.60
    Activations Density 0.004%

    No Known Activations