© 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. 22-RES-MATRYOSHKA-DC
    7. 2441
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with humor speech or performance

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    ьаж
    -0.51
    tuan
    -0.50
    ształ
    -0.48
     мәкал
    -0.45
     Datenschutzer
    -0.44
    enheim
    -0.44
    zió
    -0.44
     flags
    -0.44
     Verenig
    -0.43
     Treue
    -0.42
    POSITIVE LOGITS
     laugh
    2.31
     jokes
    2.25
     humor
    2.25
     joke
    2.23
     laughs
    2.22
     laughter
    2.20
     laughing
    2.17
     humour
    2.16
     humorous
    2.11
     Humor
    2.08
    Activations Density 0.482%

    No Known Activations