© 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. 1-CLT-HP
    7. 400
    Prev
    Next
    INDEX
    Explanations

    oscopy

    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
    oscopy
    -1.83
    oscopic
    -1.00
     âgées
    -0.85
    oskop
    -0.77
     chré
    -0.75
     colorés
    -0.75
    IsMutable
    -0.73
     imprimée
    -0.68
     scattata
    -0.68
     varandra
    -0.67
    POSITIVE LOGITS
    例文帳に追加
    0.57
     major
    0.56
     perfect
    0.55
     for
    0.52
     mention
    0.51
    o
    0.50
    Perfect
    0.48
     toward
    0.47
     towards
    0.47
    Alike
    0.47
    Activations Density 0.052%

    No Known Activations