© 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. 1162
    Prev
    Next
    INDEX
    Explanations

    road and highway system descriptions including route numbers, congestions, and planned construction.

    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
     BoxFit
    -0.68
    AndEndTag
    -0.68
    ArrowToggle
    -0.58
    UnsafeEnabled
    -0.58
    tvguidetime
    -0.54
    LabelTagHelper
    -0.51
    UnknownFieldSet
    -0.51
    watermark
    -0.50
    InitVars
    -0.48
     AssemblyProduct
    -0.48
    POSITIVE LOGITS
     route
    0.95
     traffic
    0.92
     routes
    0.92
     connecting
    0.90
     Route
    0.83
     access
    0.80
     Routes
    0.80
     connection
    0.79
     interchange
    0.78
     commuter
    0.78
    Activations Density 0.803%

    No Known Activations