© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cardiovascular metrics and measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )
    -0.66
     
    -0.61
    :
    -0.58
    N
    -0.58
    </h2>
    -0.57
    S
    -0.56
    </h3>
    -0.56
    1
    -0.56
    -0.54
    hu
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.88
    invokeLater
    0.85
     doubtnut
    0.85
     Мексичка
    0.84
    出版年
    0.84
    argout
    0.82
    ressee
    0.82
    rzost
    0.81
     дописавши
    0.81
     समीक्षक
    0.81
    Activations Density 0.004%
    No Known Activations