© 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. 17516
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking techniques and processes

    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
    SBATCH
    -0.68
    ագրություններ
    -0.64
    Parcelize
    -0.58
     each
    -0.54
    المناصب
    -0.53
    dasarkan
    -0.53
    ovico
    -0.50
    posedge
    -0.49
    Each
    -0.48
    gross
    -0.48
    POSITIVE LOGITS
    >--}}
    0.56
     @"";
    0.54
    ьаж
    0.53
     فريبيس
    0.51
     Italijanski
    0.50
    UNUSED
    0.50
    Bowl
    0.50
    ઘ
    0.50
     iStock
    0.49
    SOURCE
    0.49
    Activations Density 0.003%

    No Known Activations