© 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. 5-CLT-HP
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    Insomnia and errors

    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
    تقاوى
    -0.51
    UnusedPrivate
    -0.50
    bot
    -0.50
    ########.
    -0.50
    ower
    -0.49
    port
    -0.49
    hiri
    -0.49
     Sak
    -0.48
     tu
    -0.47
     sak
    -0.47
    POSITIVE LOGITS
     myſelf
    0.85
     Monfieur
    0.82
     itſelf
    0.78
    neſs
    0.73
     ―――――
    0.72
     $_"
    0.71
     himſelf
    0.71
     Majefty
    0.68
     themſelves
    0.68
     leaſt
    0.68
    Activations Density 0.001%

    No Known Activations