© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    devotion

    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
     devotion
    -0.94
     Devotion
    -0.87
    devo
    -0.67
    Devo
    -0.57
     devo
    -0.55
     devotional
    -0.52
    FactoryBean
    -0.47
    abandon
    -0.45
     הלא
    -0.45
     osobow
    -0.43
    POSITIVE LOGITS
    تقاوى
    1.00
    findpost
    0.97
     CreateTagHelper
    0.93
     tartalomajánló
    0.93
     bezeichneter
    0.89
     externi
    0.88
     للاسماء
    0.75
    KURZBESCHREIBUNG
    0.75
     protoimpl
    0.74
    AndEndTag
    0.74
    Activations Density 0.053%

    No Known Activations