© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94217
    Prev
    Next
    INDEX
    Explanations

    also

    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
     protoimpl
    -0.72
    хьтан
    -0.66
     AttributeSet
    -0.60
    Hozzáférés
    -0.58
     الرياضيه
    -0.58
    StoryboardSegue
    -0.57
     betweenstory
    -0.57
     Edible
    -0.57
    
    -0.57
    PerformLayout
    -0.56
    POSITIVE LOGITS
     a
    0.88
     an
    0.72
     rather
    0.69
     another
    0.64
     on
    0.56
     fairly
    0.52
     appealing
    0.52
     really
    0.50
     not
    0.49
     something
    0.49
    Activations Density 0.002%

    No Known Activations