© 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. 22-RES-MATRYOSHKA-DC
    7. 2056
    Prev
    Next
    INDEX
    Explanations

    C++ template declarations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     Италијани
    -0.76
     GenerationType
    -0.71
    reactstrap
    -0.68
    ArrowToggle
    -0.64
    webElementXpaths
    -0.63
    seamnă
    -0.63
    Havolalar
    -0.63
     AppCompatTheme
    -0.61
     >=",
    -0.60
     esternos
    -0.59
    POSITIVE LOGITS
     TEMPLATE
    0.56
     <>
    0.56
     templates
    0.55
    WebServlet
    0.54
    <>
    0.53
    ViewImports
    0.53
    regel
    0.49
     template
    0.48
     specialise
    0.47
     reng
    0.46
    Activations Density 0.005%

    No Known Activations