© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    fragment

    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
     fragment
    -1.45
    fragment
    -0.94
     Fragment
    -0.89
    
    -0.79
     fragmento
    -0.78
    ///</
    -0.75
    Hauptartikel
    -0.71
    PIECE
    -0.70
    Fragment
    -0.69
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
    ing
    1.17
    er
    0.89
    al
    0.85
    y
    0.77
    es
    0.70
    ING
    0.66
    ی
    0.63
    en
    0.56
    ous
    0.54
    tling
    0.54
    Activations Density 1.859%

    No Known Activations