© 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. 4485
    Prev
    Next
    INDEX
    Explanations

    references to laboratory procedures and sample collection related to protein, virus, or specimen processing

    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
     supply
    -0.55
    fjspx
    -0.52
    Làm
    -0.52
    createCanvas
    -0.51
    Named
    -0.50
    Failed
    -0.49
    让你
    -0.49
    VideoCapture
    -0.48
    PMailer
    -0.48
    Timed
    -0.47
    POSITIVE LOGITS
     emitted
    1.38
     exported
    1.27
     stored
    1.16
     secreted
    1.15
     downloaded
    1.14
    delivered
    1.13
     delivered
    1.11
     deposited
    1.11
    stored
    1.11
     generated
    1.10
    Activations Density 0.610%

    No Known Activations