Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73872
    Prev
    Next
    INDEX
    Explanations

    Square footage and copyright information

    np_max-act-logits · 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
     برانيه
    -0.83
    mybatisplus
    -0.76
     nakalista
    -0.69
    曖昧さ回避
    -0.69
    StoryboardSegue
    -0.66
    Hentet
    -0.65
     שוליים
    -0.65
    fjspx
    -0.64
     charms
    -0.63
     noDo
    -0.63
    POSITIVE LOGITS
     s
    0.40
    
    
    0.37
     uska
    0.36
     незавершена
    0.34
     gren
    0.33
    devamını
    0.33
    li
    0.32
     Kenya
    0.32
    {\
    0.31
     Ren
    0.31
    Activations Density 0.001%

    No Known Activations