© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1874
    Prev
    Next
    INDEX
    Explanations

    mentions of people's relationships with each other or with things.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    DoubleQuotes
    -0.55
    {}{
    -0.54
     minds
    -0.53
     createStore
    -0.53
    tisti
    -0.50
    BeginContext
    -0.50
    vail
    -0.49
    URLEncoder
    -0.49
    حياتها
    -0.49
     lives
    -0.48
    POSITIVE LOGITS
     friends
    2.03
     friend
    1.90
     colleagues
    1.74
     buddies
    1.73
    friends
    1.66
    friend
    1.61
     pals
    1.57
     teammates
    1.55
     buddy
    1.54
     colleague
    1.54
    Activations Density 0.815%

    No Known Activations