© 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. 1-CLT-HP
    7. 45552
    Prev
    Next
    INDEX
    Explanations

    restart

    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
     restart
    -0.84
     Restart
    -0.79
    Restart
    -0.69
    restart
    -0.69
     aikana
    -0.65
     lecteurs
    -0.60
     émotions
    -0.60
     journaux
    -0.60
     restarted
    -0.59
     vérit
    -0.59
    POSITIVE LOGITS
    LabelTagHelper
    0.62
     '\\;'
    0.56
    AutoScale
    0.56
    ClientSize
    0.52
     affects
    0.51
     Normdatei
    0.51
    Obrázky
    0.51
     TextInputType
    0.50
     favors
    0.50
    וויק
    0.50
    Activations Density 0.041%

    No Known Activations