© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3538
    Prev
    Next
    INDEX
    Explanations

    instances of laughter and humor

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extra
    -0.58
     fantasia
    -0.58
    例句
    -0.56
     í
    -0.55
     Mey
    -0.55
    พล
    -0.55
     Gud
    -0.54
     ent
    -0.53
     extras
    -0.53
    enter
    -0.52
    POSITIVE LOGITS
     Laughter
    1.36
     laugh
    1.27
     Laugh
    1.27
     laughter
    1.27
     Laughing
    1.23
     laughed
    1.20
     laughs
    1.16
     laughing
    1.15
    Laughter
    1.10
     lachen
    1.09
    Activations Density 0.035%

    No Known Activations