© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    concepts related to divine purpose and life lessons

    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
    oa̍t
    -0.58
    "?>
    -0.56
     kaynağından
    -0.54
     Bench
    -0.53
     volon
    -0.52
     forState
    -0.52
     Contrast
    -0.51
     Practices
    -0.51
    epen
    -0.51
    akir
    -0.50
    POSITIVE LOGITS
     fortu
    0.81
     luck
    0.81
    luck
    0.76
     Luck
    0.75
     lucky
    0.72
     divinely
    0.71
     coincidence
    0.71
    lucky
    0.70
     blessings
    0.68
     abenço
    0.67
    Activations Density 0.278%

    No Known Activations