© 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. 17108
    Prev
    Next
    INDEX
    Explanations

    references to specific software components or technical specifications

    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
    Gizmos
    -0.67
    chastic
    -0.59
    ثيق
    -0.59
     Assyrian
    -0.59
    ENGTH
    -0.57
    cosity
    -0.57
     Canarias
    -0.56
     setw
    -0.54
     presupposes
    -0.54
    bedaan
    -0.53
    POSITIVE LOGITS
    ClCompile
    3.86
    ClInclude
    0.88
     المعيارى
    0.75
     ProtoMessage
    0.67
    Vidite
    0.60
     AppBundle
    0.60
     Buren
    0.60
    styleUrls
    0.59
    msgTypes
    0.59
    __':
    0.57
    Activations Density 0.000%

    No Known Activations