© 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. 1473
    Prev
    Next
    INDEX
    Explanations

    elements of humor and playfulness in conversation

    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
     consultato
    -0.58
    ьаж
    -0.56
     виправивши
    -0.56
    AnchorStyles
    -0.56
    CodeAttribute
    -0.55
    timbangkan
    -0.55
     protoimpl
    -0.54
    PYX
    -0.54
    {}{}
    -0.53
    лючение
    -0.53
    POSITIVE LOGITS
     amusement
    1.07
     entertainment
    1.05
     entertain
    1.04
     amusements
    1.04
     playful
    0.99
     fun
    0.98
     entertained
    0.94
     entertaining
    0.93
     prank
    0.93
     amused
    0.91
    Activations Density 1.519%

    No Known Activations