© 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. 23538
    Prev
    Next
    INDEX
    Explanations

    references to comparisons and contrasts in different contexts

    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
    PerformLayout
    -0.65
    DeleteBehavior
    -0.63
    ScopeManager
    -0.63
    MemoryWarning
    -0.62
    RetentionPolicy
    -0.61
    TypedDataSet
    -0.61
    erover
    -0.59
     StringVar
    -0.56
    InjectAttribute
    -0.52
    ApiModel
    -0.51
    POSITIVE LOGITS
     unknownFields
    0.61
    ickt
    0.52
     others
    0.50
     feather
    0.50
     oprot
    0.50
    TAWA
    0.49
     terciopelo
    0.49
     tape
    0.48
    ContentView
    0.45
    ulihan
    0.45
    Activations Density 0.145%

    No Known Activations