© 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. 3603
    Prev
    Next
    INDEX
    Explanations

    formulaic programming expressions related to makefiles

    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
    OGND
    -1.18
    المناصب
    -0.89
     betweenstory
    -0.88
    aarrggbb
    -0.87
    RTEE
    -0.83
    addCriterion
    -0.82
     saites
    -0.82
    endregion
    -0.81
    awtextra
    -0.80
     resourceCulture
    -0.79
    POSITIVE LOGITS
    =$(
    0.80
    ($(
    0.78
    ="$(
    0.74
     ($(
    0.72
     aſſ
    0.72
     paſſ
    0.71
    $(
    0.70
     ſche
    0.70
    ſelf
    0.69
     ſaid
    0.69
    Activations Density 0.019%

    No Known Activations