© 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. 30428
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntax, particularly focusing on list operations and functions

    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
    :+:
    -0.64
    ########.
    -0.63
    makeConstraints
    -0.62
    tagHelperRunner
    -0.60
    WebElementEntity
    -0.60
    PostInfinity
    -0.60
    DIPSETTING
    -0.57
    RenderAtEndOf
    -0.56
     consultato
    -0.56
    Hochspringen
    -0.56
    POSITIVE LOGITS
    AsUp
    0.53
    jsonwebtoken
    0.47
    โย
    0.47
    فاض
    0.46
     lẽ
    0.46
     Dividend
    0.46
    الع
    0.45
    rdı
    0.44
     khí
    0.44
     Datum
    0.44
    Activations Density 0.095%

    No Known Activations