© 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-CLT-HP
    7. 97557
    Prev
    Next
    INDEX
    Explanations

    fossils and fractures

    np_max-act · gemini-2.0-flash
    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
     beetle
    -1.11
     beetles
    -1.05
     Cracks
    -0.91
     Paleozoic
    -0.90
     cracks
    -0.90
     Eocene
    -0.88
     Beetle
    -0.85
     weevil
    -0.85
     ainfi
    -0.85
     fractures
    -0.80
    POSITIVE LOGITS
     and
    0.52
     protoimpl
    0.49
     Williamson
    0.49
    DATABASES
    0.48
    ,
    0.47
     lit
    0.47
     theo
    0.47
     Rap
    0.47
     Tra
    0.46
     bad
    0.46
    Activations Density 1.686%

    No Known Activations