© 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. 166
    Prev
    Next
    INDEX
    Explanations

    passages about mechanical parts, guides, and connections

    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
     thickly
    -0.54
     monochrome
    -0.49
     yellowish
    -0.48
     brown
    -0.46
     browns
    -0.46
     crackling
    -0.46
     glowing
    -0.46
     Dougherty
    -0.45
     milky
    -0.44
     dark
    -0.44
    POSITIVE LOGITS
    findpost
    0.85
     spring
    0.71
    ArrowToggle
    0.70
     springs
    0.67
     support
    0.66
    UrlResolution
    0.64
    UnsafeEnabled
    0.63
    principalTable
    0.63
    RenderAtEndOf
    0.63
    lapsingToolbar
    0.62
    Activations Density 1.685%

    No Known Activations