© 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. 24445
    Prev
    Next
    INDEX
    Explanations

    data types and numeric values used in programming 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
    Искәрмәләр
    -0.97
     صوتيه
    -0.75
    BeginContext
    -0.72
     "*.
    -0.72
    hassee
    -0.71
     jScrollPane
    -0.69
     useStyles
    -0.66
     McP
    -0.65
     autorytatywna
    -0.65
    
    -0.63
    POSITIVE LOGITS
    hlí
    0.59
    NSNumber
    0.58
    anInt
    0.57
    NamedQueries
    0.57
    ******/
    0.55
    istiques
    0.54
     Bs
    0.54
     Ors
    0.53
    ệu
    0.52
     gese
    0.52
    Activations Density 0.015%

    No Known Activations