© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20367
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biochemical interactions, particularly involving proteins and lipids

    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
    Negative Logits
     invokingState
    -0.56
    +:+
    -0.51
     [*]
    -0.45
     live
    -0.42
    Live
    -0.41
    تري
    -0.41
    Pei
    -0.40
     khảo
    -0.39
    ínű
    -0.39
     Baillargeon
    -0.38
    POSITIVE LOGITS
    出版年
    0.85
    CardHeader
    0.75
    sizeCache
    0.72
    mtable
    0.70
    etheless
    0.68
    HtmlAttribute
    0.68
     Ouverture
    0.68
     continuant
    0.66
    ymce
    0.66
     beider
    0.65
    Activations Density 0.020%

    No Known Activations