© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1668
    Prev
    Next
    INDEX
    Explanations

    quitting and routine

    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
     regular
    -1.02
     regulares
    -0.78
     régulier
    -0.78
    regular
    -0.77
     réguli
    -0.75
    s
    -0.74
    Regular
    -0.71
     traditionnels
    -0.69
     conventional
    -0.68
     tradicionais
    -0.67
    POSITIVE LOGITS
     purpoſe
    1.02
     neceff
    0.96
     myſelf
    0.96
     ſtate
    0.94
     uſe
    0.89
     Jefus
    0.87
     itſelf
    0.86
     becauſe
    0.85
     fhort
    0.84
     pleaſure
    0.84
    Activations Density 0.131%

    No Known Activations