© 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. 20-CLT-HP
    7. 74667
    Prev
    Next
    INDEX
    Explanations

    Numbers and code

    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
     تضيفلها
    -1.20
    OGND
    -1.10
    GEBURTSDATUM
    -0.96
    :✨
    -0.95
     الرياضيه
    -0.90
    ThroughAttribute
    -0.87
     @"/
    -0.86
     Paglinawan
    -0.85
     ErrIntOverflow
    -0.85
    EndInit
    -0.83
    POSITIVE LOGITS
     comp
    0.66
     Re
    0.49
     Comp
    0.49
    comp
    0.48
    Comp
    0.46
    setContentView
    0.44
     para
    0.43
     t
    0.42
     Para
    0.40
     i
    0.39
    Activations Density 0.000%

    No Known Activations