© 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. 12-RES-MATRYOSHKA-DC
    7. 3158
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or results

    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
    OIS
    -0.68
    WebServlet
    -0.59
     fers
    -0.57
    lele
    -0.57
    gham
    -0.56
    shadowOpacity
    -0.55
    cote
    -0.54
     Jahres
    -0.54
    xFFFFFFFF
    -0.54
    SPAN
    -0.54
    POSITIVE LOGITS
     ilman
    0.75
     pymongo
    0.73
     décid
    0.72
     насељу
    0.71
     mulighed
    0.70
     inconn
    0.68
     Orrell
    0.68
     numberWith
    0.66
    раздо
    0.64
    SequentialGroup
    0.64
    Activations Density 0.059%

    No Known Activations