© 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. 4516
    Prev
    Next
    INDEX
    Explanations

    references to plasma or plasma concentration data

    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
     blood
    -0.78
     Blood
    -0.75
    Blood
    -0.72
     Blut
    -0.72
    blood
    -0.71
     BLOOD
    -0.69
    BLOOD
    -0.60
     sangre
    -0.57
     cappuccio
    -0.55
     Duro
    -0.53
    POSITIVE LOGITS
     plasma
    2.78
     Plasma
    2.56
    Plasma
    2.47
    plasma
    2.44
    ASMA
    1.61
     plas
    1.20
     Plas
    1.00
    lasma
    0.88
    Plas
    0.81
    plas
    0.78
    Activations Density 0.028%

    No Known Activations