© 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. 6837
    Prev
    Next
    INDEX
    Explanations

    references to sermon series or structured sequences in religious or instructional contexts

    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
     Bouch
    -0.75
    脚注の使い方
    -0.74
    SDAY
    -0.72
    lihood
    -0.71
    itects
    -0.71
    utschein
    -0.69
     Monfieur
    -0.69
    сылкі
    -0.68
    ього
    -0.67
     дописавши
    -0.66
    POSITIVE LOGITS
     Series
    1.87
    Series
    1.84
     series
    1.80
     SERIES
    1.80
    SERIES
    1.59
    series
    1.55
    iseries
    1.52
     Serie
    1.24
    Serie
    1.21
    eries
    1.20
    Activations Density 0.081%

    No Known Activations