© 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. 9495
    Prev
    Next
    INDEX
    Explanations

    references to purchasing or buying items

    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
    rungsseite
    -0.63
     ſtate
    -0.60
    ValueStyle
    -0.57
     faſt
    -0.57
    rical
    -0.56
     оригіналу
    -0.55
    lappe
    -0.55
    gste
    -0.54
    läge
    -0.54
    gue
    -0.53
    POSITIVE LOGITS
     purchased
    0.95
     bought
    0.92
     purchase
    0.88
     membeli
    0.79
    purchase
    0.79
     purchasing
    0.77
     purchases
    0.76
    purchased
    0.76
    Bought
    0.73
    bought
    0.71
    Activations Density 0.108%

    No Known Activations