© 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. 30881
    Prev
    Next
    INDEX
    Explanations

    non-verbal textual elements, such as structure and formatting indicators

    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
    ninth
    -0.56
    descent
    -0.55
     CascadeType
    -0.54
    ALTY
    -0.53
     deeper
    -0.51
    worldwide
    -0.51
     Terrell
    -0.51
    نائ
    -0.48
    сылкі
    -0.48
    Bibliograf
    -0.48
    POSITIVE LOGITS
    LookAnd
    0.65
     Zustimmung
    0.61
    PreferredItem
    0.60
     Réponses
    0.59
     fieldNum
    0.58
    RefNanny
    0.57
    !*\
    0.56
     numberOfRows
    0.52
     mouseY
    0.51
    cloudfront
    0.50
    Activations Density 0.024%

    No Known Activations