© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, in the text

    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
    Datuak
    -0.94
     дописавши
    -0.90
    脚注の使い方
    -0.87
    IndentedString
    -0.85
    例文帳に追加
    -0.84
     ModelExpression
    -0.80
     mergeFrom
    -0.80
     digress
    -0.78
    __()
    -0.77
    RenderAtEndOf
    -0.77
    POSITIVE LOGITS
     real
    0.50
    gg
    0.45
    shutil
    0.45
     I
    0.45
     both
    0.45
    SizeF
    0.44
    ,
    0.42
     col
    0.42
    ars
    0.42
     section
    0.42
    Activations Density 0.002%

    No Known Activations