© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    references to specific surgical techniques used in vascular or organ transplant procedures

    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
    sendKeys
    -0.38
    招
    -0.37
    RT
    -0.36
    GEBURTSDATUM
    -0.36
     huis
    -0.35
    初
    -0.35
    ونا
    -0.35
     Symptoms
    -0.34
    嘶
    -0.34
    </h3>
    -0.34
    POSITIVE LOGITS
     Efq
    1.09
     purpoſe
    0.94
     uſed
    0.91
     ―――――
    0.90
     ſeveral
    0.90
     ſte
    0.89
     myſelf
    0.89
     doubtnut
    0.88
     fhew
    0.88
     poffe
    0.87
    Activations Density 1.168%

    No Known Activations