© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45353
    Prev
    Next
    INDEX
    Explanations

    technical and martial arts

    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
    er
    -0.57
    ing
    -0.55
    ly
    -0.53
    ORAGE
    -0.51
     far
    -0.44
     tri
    -0.43
    
    -0.43
    Shape
    -0.42
     Himo
    -0.41
    ,
    -0.41
    POSITIVE LOGITS
     myſelf
    0.92
     Monfieur
    0.92
     pleaſure
    0.87
     Jefus
    0.86
     themſelves
    0.83
     raiſ
    0.82
     itſelf
    0.81
     reaſon
    0.77
     juſ
    0.77
     ſtand
    0.75
    Activations Density 0.502%

    No Known Activations