© 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. 20118
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships and interactions

    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
     Int
    -0.65
     py
    -0.65
     PopupWindow
    -0.62
     Ackerman
    -0.61
     <<<<<<<<<<<<<<
    -0.60
     pal
    -0.58
     ple
    -0.58
    eakers
    -0.58
     Pierson
    -0.58
     pem
    -0.57
    POSITIVE LOGITS
    存于互联网档案馆
    0.96
    RenderAtEndOf
    0.96
    ########.
    0.92
     us
    0.77
     mình
    0.73
     дописавши
    0.73
     lära
    0.72
    ValueStyle
    0.71
     autorytatywna
    0.69
     مشين
    0.68
    Activations Density 0.138%

    No Known Activations