© 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. 17288
    Prev
    Next
    INDEX
    Explanations

    contexts related to mathematical definitions and conditions involving functions and variables

    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
    IUrlHelper
    -0.83
     Hift
    -0.82
     Cæsar
    -0.75
     avoit
    -0.71
     autorytatywna
    -0.70
     itſelf
    -0.69
     ་་
    -0.68
     Serbs
    -0.68
     haram
    -0.67
     Lira
    -0.67
    POSITIVE LOGITS
    rawDesc
    0.57
     open
    0.56
    VELOP
    0.51
    anyika
    0.50
    prnewswire
    0.50
    chette
    0.50
     Che
    0.50
     stop
    0.49
    hlí
    0.49
     stand
    0.48
    Activations Density 0.084%

    No Known Activations