© 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. 91202
    Prev
    Next
    INDEX
    Explanations

    thought

    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
     thought
    -1.92
     Thought
    -1.36
    Thought
    -1.29
     THOUGHT
    -1.28
    thought
    -1.21
     pensée
    -0.86
     pensiero
    -0.75
     thinking
    -0.70
     believed
    -0.70
     tanke
    -0.67
    POSITIVE LOGITS
    setVerticalGroup
    0.87
     createState
    0.86
    abestanden
    0.83
    complexContent
    0.82
    Према
    0.76
    脚注の使い方
    0.75
     jScrollPane
    0.75
    :+:
    0.70
    ########.
    0.70
    
    0.69
    Activations Density 0.014%

    No Known Activations