© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15265
    Prev
    Next
    INDEX
    Explanations

    references to solar eclipses, particularly those emphasizing the rarity and significance of total solar eclipses

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Географиясе
    -0.69
    pulumi
    -0.65
    mybatisplus
    -0.65
    SharedDtor
    -0.64
    VIAF
    -0.62
     Houſe
    -0.61
     bogotá
    -0.61
     cdti
    -0.61
     ReactDOM
    -0.60
     GPR
    -0.60
    POSITIVE LOGITS
     Eclipse
    3.23
     eclipse
    2.77
    Eclipse
    2.63
     eclips
    2.09
    eclipse
    1.36
     eclip
    1.30
    lipse
    0.86
    clips
    0.70
    ECL
    0.63
    MathML
    0.54
    Activations Density 0.001%

    No Known Activations