© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38808
    Prev
    Next
    INDEX
    Explanations

    pie

    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
     empire
    -0.79
     pie
    -0.77
    ie
    -0.73
    eg
    -0.70
     empires
    -0.64
     Empire
    -0.63
    pie
    -0.62
     Empires
    -0.61
     monarchy
    -0.57
    ii
    -0.56
    POSITIVE LOGITS
    EndProject
    0.68
     autorytatywna
    0.66
     myſelf
    0.66
     pleaſure
    0.65
    出版年
    0.64
     تانيه
    0.63
    ſelves
    0.62
     TestBed
    0.62
     ſhall
    0.61
     ―――――
    0.60
    Activations Density 0.122%

    No Known Activations