© 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. 30196
    Prev
    Next
    INDEX
    Explanations

    references to legal terms or concepts

    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
    httphttps
    -0.83
     saites
    -0.71
     متعلقه
    -0.71
    存于互联网档案馆
    -0.68
    BagLayout
    -0.62
    ArgsConstructor
    -0.61
    endenza
    -0.61
     الدولى
    -0.61
     esternos
    -0.60
    niająca
    -0.59
    POSITIVE LOGITS
     band
    0.54
     law
    0.52
    jaardag
    0.51
     week
    0.48
    pon
    0.46
     Закон
    0.46
     tip
    0.45
     bro
    0.45
    askar
    0.45
     normalidad
    0.45
    Activations Density 0.001%

    No Known Activations