© 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. 19106
    Prev
    Next
    INDEX
    Explanations

    references to specific character names and their interactions

    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
    eddable
    -0.55
    :^(
    -0.54
    érêt
    -0.50
    /*
    -0.50
    BeginContext
    -0.49
     guapos
    -0.49
    şık
    -0.48
    Finite
    -0.48
    /*:
    -0.48
     JADX
    -0.47
    POSITIVE LOGITS
    webElementXpaths
    0.90
    Personensuche
    0.81
    sizeCache
    0.74
    IsMutable
    0.73
    parsedMessage
    0.72
    Попис
    0.71
     Walkover
    0.67
     Biôgrafia
    0.63
    expandindo
    0.62
     @"/
    0.60
    Activations Density 0.003%

    No Known Activations