© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19179
    Prev
    Next
    INDEX
    Explanations

    references to specific locations in Alaska and their corresponding features

    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
     AssemblyProduct
    -0.77
    pyplot
    -0.73
    flink
    -0.69
    TypedDataSet
    -0.66
     EventArgs
    -0.66
     MessageBoxIcon
    -0.64
    GeneratedMessage
    -0.62
    फ्त
    -0.61
     Amon
    -0.61
    PerformLayout
    -0.59
    POSITIVE LOGITS
     Alaska
    1.46
    Alaska
    1.36
     alaska
    1.25
     Alaskan
    1.23
     Fairbanks
    1.17
     polaire
    1.17
     Juneau
    1.06
     Anchorage
    1.05
     tundra
    1.02
    alaska
    0.98
    Activations Density 0.041%

    No Known Activations