© 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. 22-RES-MATRYOSHKA-DC
    7. 3252
    Prev
    Next
    INDEX
    Explanations

    phrases that include "in" and "order" or otherwise indicate that something needs to happen within something else

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyTitle
    -0.68
     disambiguazione
    -0.64
    ="@+
    -0.61
    complexContent
    -0.59
    
    -0.57
    ❮
    -0.57
     Савезне
    -0.56
    QMetaType
    -0.56
    InitVars
    -0.53
    tifact
    -0.53
    POSITIVE LOGITS
     order
    2.89
    order
    2.34
     ORDER
    2.03
     Order
    2.00
    Order
    1.97
    ORDER
    1.84
     ordem
    1.54
     ordre
    1.52
     orders
    1.47
     orden
    1.45
    Activations Density 0.296%

    No Known Activations