© 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. 24955
    Prev
    Next
    INDEX
    Explanations

    brand names and popular product mentions

    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
    HomeAsUpEnabled
    -0.71
    extAlignment
    -0.67
    Derbyniad
    -0.66
    RenderAtEndOf
    -0.66
    DockStyle
    -0.64
    adaptiveStyles
    -0.64
    UserScript
    -0.62
     الحره
    -0.61
    erialization
    -0.61
     /\.(
    -0.61
    POSITIVE LOGITS
    __()
    0.54
    قد
    0.52
    mybatisplus
    0.49
    ReadKey
    0.48
    providedIn
    0.48
    stateProvider
    0.47
     supply
    0.47
    mbggenerated
    0.46
     речь
    0.46
     maig
    0.45
    Activations Density 0.001%

    No Known Activations