© 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. 24-RES-MATRYOSHKA-DC
    7. 862
    Prev
    Next
    INDEX
    Explanations

    Microsoft products

    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.24.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.24.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
     CreateTagHelper
    -0.60
    extAlignment
    -0.60
     ExecuteAsync
    -0.59
     समीक्षाओं
    -0.56
    RectangleBorder
    -0.55
    AndEndTag
    -0.55
     Bronson
    -0.54
    IntoConstraints
    -0.53
     estekak
    -0.52
     cherchés
    -0.52
    POSITIVE LOGITS
     Windows
    0.78
    Windows
    0.71
     Microsoft
    0.68
     windows
    0.66
    Microsoft
    0.63
     MS
    0.63
     WINDOWS
    0.62
    windows
    0.59
     Office
    0.57
     Exchange
    0.57
    Activations Density 0.979%

    No Known Activations