© 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. 10446
    Prev
    Next
    INDEX
    Explanations

    genes and their expressions related to specific molecular functions or characteristics in a biological context

    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
     tongs
    -0.52
    mappedBy
    -0.46
    InputTagHelper
    -0.45
     transfieras
    -0.45
    skip
    -0.44
    órmulas
    -0.44
     EdgeInsets
    -0.43
     Schö
    -0.43
     Loaded
    -0.43
    Skip
    -0.43
    POSITIVE LOGITS
    parsedMessage
    0.72
     дописавши
    0.68
    arition
    0.64
     EClass
    0.64
    :✨
    0.64
    Parcelize
    0.63
     nakalista
    0.62
    ameters
    0.62
    endphp
    0.62
    (;;)
    0.61
    Activations Density 0.139%

    No Known Activations