© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45209
    Prev
    Next
    INDEX
    Explanations

    Medical conditions or weather

    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
    ained
    -0.57
     
    -0.56
    ly
    -0.52
     Ma
    -0.52
     p
    -0.52
    lo
    -0.52
     ang
    -0.51
     mit
    -0.51
     ha
    -0.49
     m
    -0.48
    POSITIVE LOGITS
     propOrder
    1.13
    UserScript
    0.96
     auroit
    0.91
     auffi
    0.90
    
    0.89
     '\\;'
    0.88
     تضيفلها
    0.87
    ſelves
    0.84
    addPreferredGap
    0.84
    RenderAtEndOf
    0.83
    Activations Density 0.212%

    No Known Activations