© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    keywords associated with diseases and their risk factors

    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
    تقاوى
    -1.03
    Personensuche
    -1.00
     itſelf
    -0.99
    ंदीखरीदारी
    -0.98
     Theſe
    -0.98
     تضيفلها
    -0.95
    IndentedString
    -0.95
     مشين
    -0.93
    SharedCtor
    -0.91
     pinulongan
    -0.91
    POSITIVE LOGITS
     plus
    0.59
    plus
    0.53
     and
    0.47
    <bos>
    0.44
     including
    0.44
     along
    0.44
     sowie
    0.43
    along
    0.42
     samt
    0.42
     inclusive
    0.42
    Activations Density 0.255%

    No Known Activations