© 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. 23195
    Prev
    Next
    INDEX
    Explanations

    references to outlines or structured plans

    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
    imedia
    -0.81
    transQ
    -0.78
     LIBR
    -0.67
    scho
    -0.66
    HasColumnType
    -0.65
     yat
    -0.65
     espont
    -0.65
    bidities
    -0.65
     AssemblyCulture
    -0.65
     streams
    -0.64
    POSITIVE LOGITS
     outline
    1.36
    Outline
    1.31
     Outline
    1.31
    outline
    1.21
     outlines
    1.15
     outlined
    1.05
     outlining
    1.05
    outlined
    0.95
     OUTLINE
    0.95
     InputDecoration
    0.87
    Activations Density 0.005%

    No Known Activations