© 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. 2-RES-MATRYOSHKA-DC
    7. 2977
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "top" or "top of" indicating prominence or the highest position

    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
     below
    -0.95
    below
    -0.91
     Below
    -0.88
     BELOW
    -0.88
     lower
    -0.84
    Below
    -0.80
     Lower
    -0.77
    Lower
    -0.76
    lower
    -0.73
     LOWER
    -0.73
    POSITIVE LOGITS
     top
    2.83
    top
    2.73
    Top
    2.61
     Top
    2.61
    TOP
    2.38
     TOP
    2.36
     tops
    2.03
    tops
    1.96
     Tops
    1.76
    トップ
    1.70
    Activations Density 0.106%

    No Known Activations