© 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. 15837
    Prev
    Next
    INDEX
    Explanations

    phrases expressing preference or comparison

    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
    ⓧ
    -0.75
    AccessorTable
    -0.74
    WithIOException
    -0.74
    OwnProperty
    -0.73
     disponibilités
    -0.71
     >=",
    -0.69
    jspx
    -0.67
    iastes
    -0.67
    msgTypes
    -0.65
    ArrowToggle
    -0.65
    POSITIVE LOGITS
    ubli
    0.57
    offen
    0.55
    acán
    0.54
     sedia
    0.53
     categoryId
    0.52
    elor
    0.51
    acan
    0.51
     basta
    0.51
    matum
    0.50
    instancetype
    0.50
    Activations Density 0.019%

    No Known Activations