© 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. 32028
    Prev
    Next
    INDEX
    Explanations

    instances of selection or designation in a study context

    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
     myſelf
    -0.62
     Eſ
    -0.57
     itſelf
    -0.57
     ſche
    -0.57
     Reſ
    -0.57
    BibitemShut
    -0.55
    ſtanding
    -0.54
    ftances
    -0.54
     themſelves
    -0.52
     ſp
    -0.52
    POSITIVE LOGITS
    AndEndTag
    1.15
    mergeFrom
    0.86
    +#+#
    0.84
    BeginContext
    0.79
    SourceChecksum
    0.78
     jspb
    0.73
    AddTagHelper
    0.71
     fieldNum
    0.71
    GenerationType
    0.67
    setVerticalGroup
    0.64
    Activations Density 0.082%

    No Known Activations