© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    expressions related to religious beliefs and accountability

    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
     already
    -0.80
    already
    -0.71
     allerede
    -0.66
     ALREADY
    -0.66
    Архівовано
    -0.65
    Already
    -0.63
    aimerais
    -0.63
    ChildScrollView
    -0.61
    ALREADY
    -0.60
     Already
    -0.60
    POSITIVE LOGITS
    CPtr
    0.57
     apport
    0.56
     Rather
    0.56
    abank
    0.55
     rather
    0.54
     pokrač
    0.52
    termilk
    0.52
    だったが
    0.51
     रही
    0.51
     geweest
    0.50
    Activations Density 0.140%

    No Known Activations