© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 377
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental pollution and waste management

    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
     initComponents
    -0.93
     defaultstate
    -0.91
     propOrder
    -0.91
    цездатний
    -0.84
     actionMode
    -0.82
     diphtheria
    -0.81
    省市镇
    -0.78
     بيها
    -0.77
     мәкал
    -0.77
     onOptions
    -0.76
    POSITIVE LOGITS
     materials
    0.69
     products
    0.68
     contents
    0.63
    ImageField
    0.62
     material
    0.62
     storage
    0.59
    sprodu
    0.58
    materials
    0.56
     materi
    0.56
     waste
    0.55
    Activations Density 8.879%

    No Known Activations