© 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. 38922
    Prev
    Next
    INDEX
    Explanations

    ired

    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
     greateſt
    -1.14
     themſelves
    -1.08
     itſelf
    -1.02
     Shakspeare
    -1.00
     myſelf
    -1.00
     pleaſure
    -0.99
     doubtnut
    -0.99
     leſs
    -0.96
     reaſon
    -0.93
     raiſ
    -0.92
    POSITIVE LOGITS
    ️
    0.66
    ly
    0.54
    al
    0.50
     z
    0.50
     h
    0.49
    с
    0.48
     Ze
    0.47
     min
    0.47
     sui
    0.46
    ze
    0.46
    Activations Density 0.106%

    No Known Activations