© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 741
    Prev
    Next
    INDEX
    Explanations

    road and highway-related terms and designations

    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.22.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.22.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
    CardContent
    -0.58
    UnsafeEnabled
    -0.56
     Exacts
    -0.56
    AntiForgeryToken
    -0.56
    MLLoader
    -0.55
    becher
    -0.54
     seated
    -0.53
    setContentView
    -0.52
    ModelSerializer
    -0.52
     sitting
    -0.50
    POSITIVE LOGITS
     connecting
    1.27
     linking
    1.12
     crossing
    1.09
    connecting
    1.05
     route
    1.05
     connects
    1.04
     connect
    1.01
     menghub
    0.96
     passing
    0.96
     Connecting
    0.96
    Activations Density 1.236%

    No Known Activations