Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1454
    Prev
    Next
    INDEX
    Explanations

    certainly

    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
    +#+#
    -1.00
     Monfieur
    -0.92
    Попис
    -0.90
     Anſ
    -0.86
     Jefus
    -0.86
     myſelf
    -0.86
     itſelf
    -0.85
     Efq
    -0.84
     themſelves
    -0.82
     greateſt
    -0.82
    POSITIVE LOGITS
     que
    0.43
    });
    
    0.41
    :
    0.40
    )=>{
    
    0.40
     }}^{
    0.39
    })
    
    0.39
     που
    0.38
     vart
    0.36
     который
    0.36
     });
    
    0.36
    Activations Density 0.013%

    No Known Activations