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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16267
    Prev
    Next
    INDEX
    Explanations

    HTML table cell structure

    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
     autorytatywna
    -0.86
    RegistryLite
    -0.67
    MessageOf
    -0.66
     Chwiliwch
    -0.66
    homonymie
    -0.65
    PositiveButton
    -0.64
    ensuche
    -0.62
    writeFieldEnd
    -0.60
    lorette
    -0.59
    énario
    -0.59
    POSITIVE LOGITS
     GenerationType
    0.66
     sooner
    0.45
     propOrder
    0.45
     ladrillo
    0.44
     surely
    0.43
    LinkId
    0.42
    Kok
    0.41
     кстати
    0.41
     algun
    0.41
     aprendiz
    0.41
    Activations Density 0.003%

    No Known Activations