© 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. 22242
    Prev
    Next
    INDEX
    Explanations

    references to quantities, particularly involving multiple types or instances

    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
    WebElementEntity
    -0.57
    endwhile
    -0.56
    씩
    -0.55
     fallu
    -0.55
    UserScript
    -0.53
     suất
    -0.52
    ówczas
    -0.52
    anganronpa
    -0.52
    excellents
    -0.52
     apiece
    -0.50
    POSITIVE LOGITS
     للاسماء
    0.65
    Activités
    0.63
    +#+#
    0.54
    ViewChild
    0.54
     Bourgoin
    0.53
    一方面
    0.51
     DataTypes
    0.50
    ộn
    0.50
    ittarius
    0.50
    }`}>
    0.50
    Activations Density 0.122%

    No Known Activations