© 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. 0-CLT-HP
    7. 45190
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     derail
    -0.60
    ophores
    -0.53
     sie
    -0.48
    lat
    -0.47
     Remastered
    -0.46
     tra
    -0.46
     lift
    -0.46
    Dock
    -0.45
    fell
    -0.45
     contaminate
    -0.45
    POSITIVE LOGITS
    ſelf
    0.88
    tonsoft
    0.83
    ſelves
    0.81
     itſelf
    0.79
     ſy
    0.76
    neſs
    0.68
     незавершена
    0.68
     pleaſure
    0.67
     Paglinawan
    0.66
    Etimología
    0.65
    Activations Density 0.506%

    No Known Activations