© 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. 0-CLT-HP
    7. 40668
    Prev
    Next
    INDEX
    Explanations

    opening sentences

    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
     ―――――
    -2.36
     تضيفلها
    -2.34
     ་་
    -2.34
     Мексичка
    -2.30
     виправивши
    -2.30
     Efq
    -2.22
     itſelf
    -2.22
     myſelf
    -2.22
    <unused1>
    -2.19
    <unused23>
    -2.19
    POSITIVE LOGITS
    .
    1.70
     
    1.69
    ↵
    1.59
    ,
    1.46
    :
    1.41
    ↵↵
    1.38
    -
    1.36
    '
    1.36
     (
    1.32
      
    1.28
    Activations Density 0.069%

    No Known Activations