© 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. 486
    Prev
    Next
    INDEX
    Explanations

    the presence of technical terms related to medical procedures and analysis

    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
     AssemblyCulture
    -0.92
    ImageField
    -0.75
    +#+#
    -0.73
    StructEnd
    -0.70
    룹
    -0.69
    ymce
    -0.68
    Itoa
    -0.68
    tableFuture
    -0.66
     truss
    -0.65
    valently
    -0.65
    POSITIVE LOGITS
    ization
    1.14
    vation
    0.96
    '));
    0.95
    ation
    0.92
    alisation
    0.88
    fication
    0.88
    ration
    0.87
    "]);
    0.87
    uration
    0.87
    idation
    0.86
    Activations Density 4.498%

    No Known Activations