© 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. 45
    Prev
    Next
    INDEX
    Explanations

    mentions of paths, trails, rivers, and travel more generally.

    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
    tvguidetime
    -0.92
     الحره
    -0.90
    AddTagHelper
    -0.86
     vectorielles
    -0.80
    AddHtmlAttribute
    -0.79
     pensée
    -0.79
     élas
    -0.79
     الدولى
    -0.79
     AssemblyCulture
    -0.74
    AndEndTag
    -0.74
    POSITIVE LOGITS
     nearby
    1.09
     northern
    1.05
     southern
    1.04
     inland
    1.03
     south
    1.02
     eastern
    1.01
     coastal
    1.01
     north
    0.99
     east
    0.98
     west
    0.97
    Activations Density 7.833%

    No Known Activations