© 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. 9153
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce assumptions or considerations

    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
     Because
    -0.65
    Because
    -0.65
     Porque
    -0.64
    Cuz
    -0.59
     cause
    -0.59
     because
    -0.57
     CAUSE
    -0.57
    racuse
    -0.56
     causes
    -0.54
     causa
    -0.53
    POSITIVE LOGITS
    AddHtmlAttribute
    0.91
    makeText
    0.82
     typelib
    0.80
    BagLayout
    0.80
     StatefulWidget
    0.78
     MainAxisSize
    0.78
    Nuorodos
    0.76
    IntoConstraints
    0.76
    LabelTagHelper
    0.75
    Šaltiniai
    0.74
    Activations Density 0.047%

    No Known Activations