© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9138
    Prev
    Next
    INDEX
    Explanations

    references to the term "recipient" or related words indicating a person who receives something

    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
    Negative Logits
    ogia
    -0.80
     Lawler
    -0.64
     Winder
    -0.62
    例句
    -0.62
     Linde
    -0.61
     Mow
    -0.60
    WebElementEntity
    -0.59
     dům
    -0.59
    șe
    -0.59
     venons
    -0.59
    POSITIVE LOGITS
    Recipient
    1.32
     Recipients
    1.28
     Recipient
    1.26
     recipient
    1.25
    recipient
    1.23
    Recipients
    1.16
     RECIP
    1.15
     recipients
    1.14
    RECIP
    1.10
    recipients
    1.01
    Activations Density 0.003%

    No Known Activations