© 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. 18-RES-MATRYOSHKA-DC
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    instances of particular formatting in the document, with a focus on numbers at the beginning of lines

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    RenderAtEndOf
    -1.15
    StoryboardSegue
    -0.77
    __":
    -0.77
    yntaxException
    -0.74
    WritableDatabase
    -0.71
     MainAxisSize
    -0.70
     repatriation
    -0.68
     Baillargeon
    -0.68
    __':
    -0.66
     تانيه
    -0.65
    POSITIVE LOGITS
    <bos>
    0.55
    msgSender
    0.46
    省市镇
    0.42
    flop
    0.40
    łada
    0.40
    IndentedString
    0.39
    unks
    0.38
    agraph
    0.38
    vark
    0.38
    ----</
    0.37
    Activations Density 0.067%

    No Known Activations