© 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. 91047
    Prev
    Next
    INDEX
    Explanations

    exiled

    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
     moving
    -0.96
    Spotted
    -0.94
     reinforce
    -0.79
     Spotted
    -0.78
    moving
    -0.76
     reinforcing
    -0.74
     Moving
    -0.73
    Moving
    -0.66
     spotted
    -0.66
    spotted
    -0.64
    POSITIVE LOGITS
    fromnode
    0.64
     '\\;'
    0.63
     pinulongan
    0.58
     الرياضيه
    0.57
    
    0.56
     Olímpicos
    0.53
    avigation
    0.52
     InputDecoration
    0.52
     poire
    0.50
    doe
    0.50
    Activations Density 0.041%

    No Known Activations