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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74186
    Prev
    Next
    INDEX
    Explanations

    general news snippets

    np_max-act-logits · gemini-2.0-flash

    references to Texas and Texas-related proper nouns or institutions.

    oai_token-act-pair · o3Triggered by @giuseppebirardi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Texas
    -1.41
     Texas
    -1.39
     TEXAS
    -1.36
     Texan
    -1.21
     TX
    -1.19
     texas
    -1.17
    TEXAS
    -1.13
    Dallas
    -1.11
     Dallas
    -1.10
    texas
    -1.03
    POSITIVE LOGITS
     MUNDO
    0.59
     Arenas
    0.49
     contextLoads
    0.48
     Abreu
    0.48
     становника
    0.47
     Puente
    0.46
     Leandro
    0.46
    ysty
    0.46
     Muerte
    0.46
    spesies
    0.46
    Activations Density 0.067%

    No Known Activations