© 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. 15040
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts that include the word "on."

    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
    IUrlHelper
    -0.97
    IsContent
    -0.88
    </thead>
    -0.85
    PostExecute
    -0.82
    InjectAttribute
    -0.79
    RenderAtEndOf
    -0.77
    AddHtmlAttribute
    -0.76
     ModelExpression
    -0.75
    WebControls
    -0.75
    icoot
    -0.73
    POSITIVE LOGITS
     Ston
    0.84
    ed
    0.77
    wür
    0.75
    don
    0.71
    on
    0.70
    pion
    0.67
     Huron
    0.67
    ON
    0.66
     behalf
    0.66
    lon
    0.66
    Activations Density 0.055%

    No Known Activations