© 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. 5281
    Prev
    Next
    INDEX
    Explanations

    references to compassion, respect, and humane treatment in educational contexts

    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
    ↵↵
    -0.57
     if
    -0.48
     
    -0.48
     A
    -0.47
    ase
    -0.47
    if
    -0.46
     [
    -0.46
     an
    -0.44
     Pa
    -0.43
    배
    -0.43
    POSITIVE LOGITS
     nahilalakip
    1.06
    verwijspagina
    0.96
    ftagPool
    0.95
     المعيارى
    0.94
     kasarigan
    0.94
     دیکھیے
    0.93
     незавершена
    0.91
    MLLoader
    0.91
     تضيفلها
    0.90
    AsUp
    0.89
    Activations Density 0.643%

    No Known Activations