© 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. 243
    Prev
    Next
    INDEX
    Explanations

    mentions of the Peshekee River in Michigan

    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
     المعيارى
    -0.68
     membrana
    -0.57
    providedIn
    -0.54
    parsedMessage
    -0.53
     intestino
    -0.52
     Hawaii
    -0.51
    ALIAN
    -0.51
     Honolulu
    -0.49
     işe
    -0.49
    躇
    -0.49
    POSITIVE LOGITS
     north
    1.02
     south
    1.00
     northwest
    0.97
     east
    0.96
     eastern
    0.93
     west
    0.92
     inland
    0.92
     picturesque
    0.91
     northern
    0.91
     northwestern
    0.90
    Activations Density 2.663%

    No Known Activations