© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14443
    Prev
    Next
    INDEX
    Explanations

    expressions of laughing or smiling

    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
     laugh
    -0.69
     shout
    -0.62
    shout
    -0.60
    laugh
    -0.56
    Hentet
    -0.54
    lossians
    -0.53
    prnewswire
    -0.52
     stare
    -0.51
    Ouch
    -0.49
    جوايز
    -0.49
    POSITIVE LOGITS
     smiling
    1.71
     laughing
    1.65
     crying
    1.40
     Smiling
    1.34
     Laughing
    1.30
     weeping
    1.29
     giggling
    1.25
     grinning
    1.23
     Crying
    1.22
     sobbing
    1.17
    Activations Density 0.008%

    No Known Activations