© 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. 23607
    Prev
    Next
    INDEX
    Explanations

    the presence of punctuation, specifically periods

    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
    Parcelize
    -0.61
     pylab
    -0.59
    offe
    -0.58
     Reine
    -0.58
    addColumn
    -0.57
    wegg
    -0.57
     bpy
    -0.57
     来自
    -0.56
     sheet
    -0.56
     caz
    -0.55
    POSITIVE LOGITS
    /*
    0.76
    "}")
    0.75
    protetor
    0.73
     fallecimiento
    0.71
    dfunding
    0.69
    Portail
    0.67
     ")");
    0.67
    μία
    0.67
     onely
    0.67
     avoient
    0.66
    Activations Density 0.010%

    No Known Activations