© 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. 15299
    Prev
    Next
    INDEX
    Explanations

    the repeated occurrence of the word "org," indicating references to organizations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gö
    -0.44
    SourceChecksum
    -0.43
     .
    -0.43
     site
    -0.43
    chim
    -0.43
     Z
    -0.42
    му
    -0.42
     CH
    -0.41
    C
    -0.41
     Ron
    -0.41
    POSITIVE LOGITS
    ########.
    0.95
     дописавши
    0.92
     itſelf
    0.88
     nahilalakip
    0.86
     autorytatywna
    0.79
    Geplaatst
    0.79
    EndGlobalSection
    0.78
     Réponses
    0.78
     photolibrary
    0.77
    >\<^
    0.77
    Activations Density 0.002%

    No Known Activations