© 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. 2-RES-MATRYOSHKA-DC
    7. 4416
    Prev
    Next
    INDEX
    Explanations

    references to humor, jokes, or amusing content

    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
    MigrationBuilder
    -0.73
    AndEndTag
    -0.69
     povezave
    -0.63
    DESCRIPTOR
    -0.59
    migrationBuilder
    -0.58
     nakalista
    -0.58
    ecore
    -0.57
    oodoo
    -0.56
     Ando
    -0.56
    stonia
    -0.56
    POSITIVE LOGITS
     laugh
    2.88
     laughs
    2.64
     joke
    2.61
     laughter
    2.56
     laughing
    2.53
     jokes
    2.53
     laughed
    2.52
     humor
    2.42
     Laughter
    2.34
     humour
    2.28
    Activations Density 0.107%

    No Known Activations