© 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. 26717
    Prev
    Next
    INDEX
    Explanations

    culinary measurement terms and cooking-related actions

    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
     ExecuteAsync
    -0.69
     serra
    -0.66
     ziua
    -0.63
    RATES
    -0.61
     насељу
    -0.61
     Lynx
    -0.60
     Hecht
    -0.59
     Palma
    -0.58
    RouterModule
    -0.58
     sworn
    -0.57
    POSITIVE LOGITS
     cups
    1.16
     spoon
    1.09
     cup
    1.02
     Jug
    1.02
    spoon
    1.02
     spoonful
    1.02
     ladle
    1.01
     Spoon
    0.99
     Cups
    0.98
     teaspoons
    0.94
    Activations Density 0.029%

    No Known Activations