© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 379
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials, appendices, and additional information in academic texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.88
    Personendaten
    -0.80
    tanleria
    -0.78
     AssemblyVersion
    -0.75
    (!__
    -0.75
     hambre
    -0.68
     CreateTagHelper
    -0.66
    }],
    -0.66
    Diweddarwch
    -0.64
     Jurí
    -0.64
    POSITIVE LOGITS
    Supplementary
    0.73
     Supplementary
    0.66
     supplementary
    0.65
    lementary
    0.65
     appendix
    0.60
     supplemental
    0.60
    Приложение
    0.60
     Waray
    0.57
    Supplement
    0.57
     additional
    0.56
    Activations Density 0.756%

    No Known Activations