© 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. 28338
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of specific individuals or entities involved in a case

    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
    ViewFeatures
    -0.56
     Chriftian
    -0.55
     OFDb
    -0.54
    selves
    -0.54
    queryInterface
    -0.53
    tront
    -0.52
     Италијани
    -0.52
     mères
    -0.52
    ]='\
    -0.51
     naman
    -0.50
    POSITIVE LOGITS
    IMPORTED
    0.66
     comigo
    0.61
     محفوظة
    0.58
    LayoutStyle
    0.57
     conmigo
    0.54
    \{\\
    0.54
     Olímpicos
    0.54
    jooq
    0.53
     مشين
    0.52
    coledì
    0.52
    Activations Density 0.027%

    No Known Activations