© 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. 5790
    Prev
    Next
    INDEX
    Explanations

    references to blood vessels or vascular structures

    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
    mphs
    -0.65
    readdir
    -0.61
     чере
    -0.56
    VIAF
    -0.56
    kasten
    -0.55
    labus
    -0.54
     parallelogram
    -0.54
     cassette
    -0.54
     Näch
    -0.54
     behö
    -0.53
    POSITIVE LOGITS
     vessel
    2.69
     vessels
    2.66
    vessel
    2.34
     Vessels
    2.30
     Vessel
    2.27
    Vessel
    2.13
    vessels
    2.02
     vaisseaux
    1.11
     navires
    1.02
     navire
    0.94
    Activations Density 0.003%

    No Known Activations