© 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. 97721
    Prev
    Next
    INDEX
    Explanations

    Random data, abbreviations

    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
     T
    -1.66
    T
    -1.25
     t
    -1.05
     Т
    -0.81
     ت
    -0.75
     a
    -0.65
     
    -0.62
     "
    -0.60
    getT
    -0.59
     pop
    -0.58
    POSITIVE LOGITS
     auffi
    1.06
     itſelf
    1.05
     myſelf
    1.01
    ſelf
    1.00
     فريبيس
    0.99
    DockStyle
    0.96
    ſelves
    0.95
     Anſ
    0.95
     ―――――
    0.93
     Reſ
    0.93
    Activations Density 0.825%

    No Known Activations