© 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. 90748
    Prev
    Next
    INDEX
    Explanations

    commercially

    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
     myſelf
    -1.16
     pleaſure
    -1.16
     himſelf
    -1.13
     itſelf
    -1.13
     Jefus
    -1.12
     houſe
    -1.09
     ſeveral
    -1.03
     ſche
    -1.02
     themſelves
    -1.02
     Conſ
    -1.02
    POSITIVE LOGITS
    ly
    0.57
     per
    0.47
     ra
    0.46
    ു
    0.43
    ued
    0.42
     numerus
    0.42
     lente
    0.41
    тый
    0.41
    cio
    0.40
     so
    0.40
    Activations Density 0.087%

    No Known Activations