© 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. 16284
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas

    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
    basicConfig
    -0.67
     
    -0.62
     تضيفلها
    -0.61
     ModelExpression
    -0.56
     proposed
    -0.50
    tuuri
    -0.50
    וויק
    -0.49
    rijf
    -0.48
    TagMode
    -0.48
     Jack
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.87
    '],
    0.77
    '):
    0.71
    eynman
    0.71
    '},
    0.70
     ),
    0.69
    liosis
    0.69
    '];
    0.67
     oprot
    0.67
    "):
    0.66
    Activations Density 0.015%

    No Known Activations