© 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. 472
    Prev
    Next
    INDEX
    Explanations

    US place names, especially cities, counties, parishes, and states

    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
     OBITUARY
    -0.61
     <=",
    -0.61
     GenerationType
    -0.58
    RenderAtEndOf
    -0.55
    :✨
    -0.53
     pulumi
    -0.53
    TextWatcher
    -0.52
     estekak
    -0.52
    APORE
    -0.52
     Roskov
    -0.51
    POSITIVE LOGITS
     City
    0.86
     County
    0.84
     Heights
    0.80
     Area
    0.75
     Airport
    0.72
     Township
    0.71
     District
    0.69
     Selatan
    0.69
     Region
    0.67
     region
    0.67
    Activations Density 2.270%

    No Known Activations