© 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. 12382
    Prev
    Next
    INDEX
    Explanations

    references to specific auditory phenomena or sounds, often indicated by words like "oud" or "ouch"

    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
    出版年
    -0.69
     Sand
    -0.65
     parlar
    -0.61
    Sand
    -0.59
     AssemblyCulture
    -0.57
    ReusableCell
    -0.55
     دیکھیے
    -0.55
    muo
    -0.55
    σμο
    -0.54
    σιμοποι
    -0.53
    POSITIVE LOGITS
    oud
    2.53
    ouch
    1.26
    ouds
    1.04
    oup
    0.78
    ouden
    0.75
    oudh
    0.71
    oude
    0.69
    OU
    0.69
    ouder
    0.68
    oux
    0.66
    Activations Density 0.002%

    No Known Activations