© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    references to discrepancies or differences within relationships and interactions

    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
     resourceCulture
    -0.81
     jScrollPane
    -0.78
     initComponents
    -0.67
    awakeFromNib
    -0.66
    migrationBuilder
    -0.63
    igshid
    -0.59
    Personensuche
    -0.59
    DIPSETTING
    -0.58
     Pairs
    -0.57
     aapt
    -0.57
    POSITIVE LOGITS
    CPtr
    0.54
     BoxDecoration
    0.48
     CreateTagHelper
    0.45
    ┛
    0.42
     identified
    0.41
    identified
    0.41
    βε
    0.41
     conçus
    0.40
    forhold
    0.40
     devenus
    0.40
    Activations Density 0.130%

    No Known Activations