© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92038
    Prev
    Next
    INDEX
    Explanations

    time units

    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
     day
    -0.61
     way
    -0.49
    ,
    -0.47
    Newswire
    -0.45
     evening
    -0.41
     year
    -0.41
     are
    -0.41
    ire
    -0.40
     night
    -0.40
     afternoon
    -0.40
    POSITIVE LOGITS
    ########.
    0.99
     незавершена
    0.96
     للمعارف
    0.94
     betweenstory
    0.88
    ThroughAttribute
    0.87
     '\\;'
    0.87
     المعيارى
    0.86
    ंदीखरीदारी
    0.85
     transfieras
    0.85
     للاسماء
    0.85
    Activations Density 0.053%

    No Known Activations