© 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. 10436
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to versions and dates

    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
    tagext
    -1.13
    principalTable
    -1.06
    MigrationBuilder
    -0.99
     myſelf
    -0.96
    OGND
    -0.93
    Diweddarwch
    -0.91
    MessageOf
    -0.91
     itſelf
    -0.90
    StructEnd
    -0.86
     utafitiHapana
    -0.85
    POSITIVE LOGITS
    Odkazy
    0.48
     V
    0.48
     er
    0.46
     Ar
    0.46
     til
    0.46
     Nugent
    0.46
    opr
    0.45
     ar
    0.45
    eller
    0.45
    NetworkInfo
    0.45
    Activations Density 0.006%

    No Known Activations