© 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. 29643
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology, specifically focusing on genetic features and their functions

    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
    principalTable
    -0.90
    InjectAttribute
    -0.69
    Personensuche
    -0.68
     >=",
    -0.61
     باخ
    -0.60
    prefixer
    -0.60
    protoc
    -0.59
     فريبيس
    -0.59
    EndProject
    -0.59
    WriteBarrier
    -0.57
    POSITIVE LOGITS
     ARISING
    0.56
    存于互联网档案馆
    0.54
     coklat
    0.51
     mentes
    0.51
    Partnership
    0.48
     anzu
    0.47
     партнер
    0.46
     cokelat
    0.45
    ervos
    0.45
    Anwendung
    0.45
    Activations Density 0.037%

    No Known Activations