© 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. 18-RES-MATRYOSHKA-DC
    7. 506
    Prev
    Next
    INDEX
    Explanations

    words for mechanical parts or processes

    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.18.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.18.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
     Geste
    -0.63
    modelBuilder
    -0.58
     paralysis
    -0.57
    jegy
    -0.57
    idosis
    -0.56
    rrggbb
    -0.55
     wheeled
    -0.54
     licenci
    -0.54
     Baus
    -0.54
    TagMode
    -0.54
    POSITIVE LOGITS
     edges
    0.85
     sides
    0.76
     edge
    0.76
     ends
    0.75
     inside
    0.68
     bagian
    0.66
     connecting
    0.65
     laterales
    0.63
     side
    0.63
     outer
    0.63
    Activations Density 3.980%

    No Known Activations