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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2906
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to specific terms or concepts

    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
     تضيفلها
    -0.56
     <=",
    -0.46
    EndProject
    -0.45
    InputTagHelper
    -0.44
     пожалуйста
    -0.43
     يتيمه
    -0.42
     szint
    -0.42
    følgelig
    -0.41
     antemano
    -0.41
     us
    -0.41
    POSITIVE LOGITS
    SequentialGroup
    0.79
    TagMode
    0.77
    Portály
    0.72
    WireFormatLite
    0.72
    AddHtmlAttribute
    0.69
    ViewFeatures
    0.67
    httphttps
    0.66
    AsUp
    0.64
    oredCriteria
    0.63
    XMLSchema
    0.62
    Activations Density 0.446%

    No Known Activations