© 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. 38435
    Prev
    Next
    INDEX
    Explanations

    art and craftsmanship

    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
    ed
    -0.79
    ing
    -0.66
    ED
    -0.51
    es
    -0.49
    y
    -0.47
    ت
    -0.47
     kun
    -0.47
     bien
    -0.46
    edb
    -0.45
    clear
    -0.44
    POSITIVE LOGITS
     purpoſe
    0.95
     myſelf
    0.95
     Majefty
    0.93
     ―――――
    0.91
     Efq
    0.91
     Monfieur
    0.89
     Houſe
    0.86
     ſind
    0.84
     Theſe
    0.83
     Jefus
    0.83
    Activations Density 0.131%

    No Known Activations