© 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. 24830
    Prev
    Next
    INDEX
    Explanations

    certain punctuation marks and symbols, suggesting it is sensitive to formatting or structure within 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
    Personensuche
    -1.01
    parsedMessage
    -0.91
     вікі
    -0.75
    mobileqq
    -0.73
    WebVitals
    -0.72
     Wikispecies
    -0.68
    Biographie
    -0.66
    abetes
    -0.65
    onViewCreated
    -0.65
     saites
    -0.64
    POSITIVE LOGITS
    ex
    0.56
    ,$_
    0.54
     <<<<<<<<<<<<<<
    0.49
     Gleaner
    0.49
    нимание
    0.48
    '])->
    0.48
    ssa
    0.48
    semantics
    0.47
    ai
    0.46
    հ
    0.46
    Activations Density 0.112%

    No Known Activations