© 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. 6380
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "order" and its variations, indicating a focus on ordering systems or commands

    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
     tfsi
    -1.16
    etheless
    -1.15
     midline
    -1.03
    rachtet
    -1.01
    gnition
    -0.99
    bibfield
    -0.97
     $_"
    -0.97
    ^(@)
    -0.96
    $.
    -0.96
     acorns
    -0.96
    POSITIVE LOGITS
     order
    1.66
     Order
    1.59
     orders
    1.52
    order
    1.52
     ORDER
    1.49
    Order
    1.43
     Orders
    1.41
    ORDER
    1.40
    orders
    1.29
    er
    1.28
    Activations Density 0.165%

    No Known Activations