Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21382
    Prev
    Next
    INDEX
    Explanations

    references to Arizona and its related contexts, particularly in sports and geography

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Normandie
    -0.63
     Asturias
    -0.60
    ulemon
    -0.59
    ernsey
    -0.57
     Kiel
    -0.57
    archical
    -0.55
     userService
    -0.54
     Dy
    -0.53
     ני
    -0.52
    Kiel
    -0.52
    POSITIVE LOGITS
     Ariz
    1.73
     Arizona
    1.51
     ARIZONA
    1.41
    Arizona
    1.34
     arizona
    1.33
     Tucson
    1.27
     AZ
    1.23
     Phoenix
    1.20
     phoenix
    1.20
    ariz
    1.17
    Activations Density 0.038%

    No Known Activations