© 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. 5471
    Prev
    Next
    INDEX
    Explanations

    code snippets or references to "theory" and/or "th" in scientific literature

    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
     Third
    -0.83
    IActionResult
    -0.82
    Third
    -0.79
    exitRule
    -0.69
    Second
    -0.68
    entee
    -0.68
    abestanden
    -0.68
     THIRD
    -0.67
     Second
    -0.66
     third
    -0.65
    POSITIVE LOGITS
    th
    2.05
    TH
    1.59
     th
    1.23
    ths
    1.23
    Th
    1.21
     Th
    1.11
     TH
    1.03
    thd
    0.92
    THS
    0.88
    tho
    0.87
    Activations Density 0.021%

    No Known Activations