© 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. 12-RES-MATRYOSHKA-DC
    7. 28497
    Prev
    Next
    INDEX
    Explanations

    indicators of medical conditions or health-related issues

    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
     convite
    -0.60
     Saxe
    -0.60
     thanksgiving
    -0.60
     [*]
    -0.58
    ogast
    -0.57
    mability
    -0.56
     ZR
    -0.55
     pigeons
    -0.54
    ZR
    -0.54
    NSString
    -0.54
    POSITIVE LOGITS
    теризу
    0.63
    ActionCreators
    0.63
    neming
    0.56
     defaultstate
    0.56
    ignty
    0.55
     وتسجيلات
    0.55
     traces
    0.54
    ufort
    0.54
    Ể
    0.54
    forName
    0.53
    Activations Density 0.024%

    No Known Activations