© 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. 5947
    Prev
    Next
    INDEX
    Explanations

    terms related to social connections and friendships

    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
    baga
    -0.97
    Życiorys
    -0.88
    IsContent
    -0.86
    oriasis
    -0.84
     Mosley
    -0.81
     بيها
    -0.80
     uParam
    -0.77
     Theaters
    -0.77
     silenzio
    -0.76
     disponibilités
    -0.76
    POSITIVE LOGITS
     Friends
    1.58
     friends
    1.55
    friends
    1.50
     FRIENDS
    1.49
    Friends
    1.45
     Friend
    1.43
     friend
    1.38
    Friend
    1.35
     FRIEND
    1.34
    friend
    1.20
    Activations Density 0.042%

    No Known Activations