© 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. 664
    Prev
    Next
    INDEX
    Explanations

    words related to politics, government, and military service

    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
    IsContent
    -0.58
     confiable
    -0.58
    CodeAttribute
    -0.57
     XCTest
    -0.54
    WebElementEntity
    -0.52
     CENTER
    -0.51
    alleye
    -0.50
     humains
    -0.49
    IUrlHelper
    -0.49
     computadoras
    -0.48
    POSITIVE LOGITS
     £
    0.81
     London
    0.76
    -£
    0.73
    London
    0.72
     Manchester
    0.66
     Liverpool
    0.65
     Londres
    0.64
    Londres
    0.64
     Yorkshire
    0.63
     LONDON
    0.63
    Activations Density 1.152%

    No Known Activations