© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    locations, cities, and regions

    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
     AssemblyTitle
    -0.81
     GetEnumerator
    -0.77
     Roskov
    -0.75
    LogFactory
    -0.75
    IonicModule
    -0.73
     aDecoder
    -0.70
    TemporalType
    -0.70
    findpost
    -0.69
    WriteBarrier
    -0.69
     BoxFit
    -0.69
    POSITIVE LOGITS
     City
    1.21
     city
    1.18
    City
    1.02
    city
    0.95
     CITY
    0.89
    CITY
    0.75
     ciudad
    0.75
    市
    0.65
     város
    0.65
    市的
    0.65
    Activations Density 0.903%

    No Known Activations