© 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. 38866
    Prev
    Next
    INDEX
    Explanations

    formal/informational writing

    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
    AndEndTag
    -0.90
    StructEnd
    -0.87
    InjectAttribute
    -0.85
     propOrder
    -0.85
     تضيفلها
    -0.85
    WillAppear
    -0.84
    InSection
    -0.84
     Walkover
    -0.82
     disambiguazione
    -0.81
    GEBURTSDATUM
    -0.79
    POSITIVE LOGITS
     sees
    0.53
     celebrates
    0.52
     develops
    0.51
     date
    0.50
     develop
    0.50
     compares
    0.48
     developing
    0.48
     limit
    0.47
     deserves
    0.47
     move
    0.46
    Activations Density 0.032%

    No Known Activations