© 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. 23512
    Prev
    Next
    INDEX
    Explanations

    repetitive punctuation marks, particularly commas

    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
     collectons
    -0.57
     réguli
    -0.56
    ások
    -0.55
    tencent
    -0.54
    ņš
    -0.53
    osoever
    -0.53
    roh
    -0.52
    aspectj
    -0.52
    CAPTION
    -0.52
    ServiceTest
    -0.52
    POSITIVE LOGITS
    
    0.63
    MLLoader
    0.58
     doInBackground
    0.54
    complexContent
    0.54
    govine
    0.54
    {}{}
    0.53
    Cyfeiriadau
    0.50
     quack
    0.50
     DataTypes
    0.50
    endpush
    0.49
    Activations Density 0.027%

    No Known Activations