© 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. 22-RES-MATRYOSHKA-DC
    7. 2510
    Prev
    Next
    INDEX
    Explanations

    words related to city planning and development, especially about transit routes and economic growth

    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
    ArrowToggle
    -0.70
    SourceChecksum
    -0.68
    memoized
    -0.60
    ]=>
    -0.59
    Климат
    -0.58
    UnsafeEnabled
    -0.57
     disambiguazione
    -0.56
     uninsured
    -0.56
     Propriété
    -0.55
     chande
    -0.55
    POSITIVE LOGITS
     walking
    0.77
     walk
    0.71
    walking
    0.70
    walk
    0.70
     density
    0.66
    walks
    0.66
     Walking
    0.65
    VersionUID
    0.65
     pedestrian
    0.65
     densities
    0.64
    Activations Density 0.287%

    No Known Activations