© 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
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 55
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements, quantities, or proportions

    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
    issau
    -0.54
     Orrell
    -0.54
    faj
    -0.49
    yanka
    -0.48
     gezegd
    -0.48
     écrite
    -0.48
     Obrigado
    -0.48
    Ή
    -0.47
     Aseg
    -0.47
     Perseus
    -0.47
    POSITIVE LOGITS
     of
    2.77
     Of
    1.74
     OF
    1.73
    of
    1.65
     của
    1.58
    Of
    1.56
    ของ
    1.38
     ofthe
    1.35
    オブ
    1.26
     ของ
    1.24
    Activations Density 4.433%

    No Known Activations