© 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. 22-RES-MATRYOSHKA-DC
    7. 1589
    Prev
    Next
    INDEX
    Explanations

    chemical and petroleum engineering terminology, including chemical formulas, minimizing production, and related concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     AttributeSet
    -0.57
    ołnier
    -0.48
    psf
    -0.45
    Drip
    -0.44
     Wikispecies
    -0.44
     irrig
    -0.42
     Vivaldi
    -0.42
     flood
    -0.41
    Flo
    -0.41
    Flood
    -0.41
    POSITIVE LOGITS
     fuel
    1.08
    Fuel
    1.03
     fuels
    1.01
     Fuel
    1.01
     Fuels
    0.98
    fuel
    0.97
     combustion
    0.93
    FUEL
    0.90
     Combustion
    0.88
    燃料
    0.87
    Activations Density 0.657%

    No Known Activations