© 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. 21762
    Prev
    Next
    INDEX
    Explanations

    references to toys

    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
     Wicidata
    -0.84
     المعيارى
    -0.71
    avadoc
    -0.69
     Tally
    -0.68
     bå
    -0.67
     שוליים
    -0.67
    mability
    -0.67
     Anam
    -0.66
    urgical
    -0.62
    րջ
    -0.62
    POSITIVE LOGITS
     toys
    1.82
     Toy
    1.76
     Toys
    1.75
     toy
    1.70
    Toys
    1.64
    toys
    1.57
    Toy
    1.55
    toy
    1.45
     TOY
    1.45
    TOY
    1.31
    Activations Density 0.004%

    No Known Activations