© 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. 13652
    Prev
    Next
    INDEX
    Explanations

    • the expression of joy or happiness

    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
     pleasure
    -0.56
     tiet
    -0.50
     Wish
    -0.48
     comfort
    -0.47
    чко
    -0.47
    lim
    -0.46
     فريبيس
    -0.46
    +#+#
    -0.46
     Leck
    -0.46
    FFEE
    -0.45
    POSITIVE LOGITS
     joy
    2.41
     Joy
    1.88
    joy
    1.85
    Joy
    1.85
     JOY
    1.75
     joys
    1.53
    JOY
    1.48
     joyful
    1.34
    joys
    1.16
     joyous
    1.07
    Activations Density 0.003%

    No Known Activations