© 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. 3422
    Prev
    Next
    INDEX
    Explanations

    references to small quantities or degrees

    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
     Few
    -0.73
    FormTagHelper
    -0.73
    Few
    -0.72
     few
    -0.71
     FEW
    -0.71
    few
    -0.70
     SwitchCompat
    -0.63
     disponibilités
    -0.62
    をご覧ください
    -0.61
     little
    -0.58
    POSITIVE LOGITS
     biraz
    0.83
     slightly
    0.79
     Slightly
    0.79
     trochu
    0.79
    Slightly
    0.77
    slightly
    0.73
     المعيارى
    0.71
    有点
    0.69
    有點
    0.68
    Somewhat
    0.68
    Activations Density 0.017%

    No Known Activations