© 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. 28664
    Prev
    Next
    INDEX
    Explanations

    terms related to coffee and coffee establishments

    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
     bata
    -0.63
     conch
    -0.63
    swire
    -0.63
    RestController
    -0.62
     SqlDbType
    -0.62
     SDLK
    -0.62
     Rahim
    -0.62
    Salmo
    -0.61
     Rockwell
    -0.61
    liśmy
    -0.60
    POSITIVE LOGITS
     coffee
    1.98
    Coffee
    1.91
     Coffee
    1.91
    coffee
    1.88
     coffees
    1.76
     COFFEE
    1.71
     coffe
    1.68
     Coffe
    1.57
     Kaffee
    1.36
    FFEE
    1.33
    Activations Density 0.012%

    No Known Activations