© 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. 11686
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate setting or configuration instructions

    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
    AndEndTag
    -0.93
     ostavi
    -0.88
     myſelf
    -0.87
     يتيمه
    -0.85
     الحره
    -0.82
     Jefus
    -0.82
     perſon
    -0.81
     houſe
    -0.80
     itſelf
    -0.79
     Anſ
    -0.78
    POSITIVE LOGITS
     
    0.67
    nonatomic
    0.63
    
    0.53
    чив
    0.52
     <
    0.51
    zies
    0.50
     a
    0.48
    írás
    0.48
    indi
    0.47
    hav
    0.47
    Activations Density 0.046%

    No Known Activations