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. 0-CLT-HP
    4. 97860
    Prev
    Next
    INDEX
    Explanations

    malabsorption, aging

    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
    crossing
    -0.87
     Crossing
    -0.84
    Crossing
    -0.80
     aging
    -0.76
     ageing
    -0.73
     crossings
    -0.73
     evening
    -0.71
     crossing
    -0.71
    evening
    -0.68
     Evening
    -0.61
    POSITIVE LOGITS
     '\\;'
    0.58
    WriteTagHelper
    0.57
    aktery
    0.56
     tenté
    0.54
     thereunder
    0.54
     crescent
    0.53
     kasarigan
    0.53
     Majefty
    0.52
    DEPORTES
    0.51
     Ravel
    0.50
    Activations Density 0.060%

    No Known Activations