© 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. 4-CLT-HP
    7. 4438
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
     special
    -1.90
     speciale
    -1.59
    special
    -1.57
    Special
    -1.47
     Special
    -1.46
     especiales
    -1.34
     especial
    -1.33
     SPECIAL
    -1.26
     spéciale
    -1.22
    SPECIAL
    -1.21
    POSITIVE LOGITS
     itſelf
    1.05
     myſelf
    0.98
     photolibrary
    0.96
    ſelf
    0.93
     незавершена
    0.87
     ―――――
    0.84
     Efq
    0.84
     iſt
    0.83
     themſelves
    0.82
     Anſ
    0.82
    Activations Density 0.005%

    No Known Activations