© 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. 97736
    Prev
    Next
    INDEX
    Explanations

    Bullet points, copyright, Google

    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
     myſelf
    -0.94
     Efq
    -0.88
    ſelf
    -0.85
     الحره
    -0.84
     houſe
    -0.84
    )•
    -0.83
     uſ
    -0.82
     ſtate
    -0.82
     ―――――
    -0.81
     itſelf
    -0.81
    POSITIVE LOGITS
     The
    0.93
      
    0.84
     A
    0.84
       
    0.77
        
    0.75
     
    0.71
     To
    0.71
    The
    0.70
          
    0.69
         
    0.69
    Activations Density 0.029%

    No Known Activations