© 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. 44002
    Prev
    Next
    INDEX
    Explanations

    research

    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
     floors
    -1.48
     Floors
    -0.98
    entennial
    -0.98
    floors
    -0.94
    ViewFeatures
    -0.79
     resourceCulture
    -0.76
    pausal
    -0.72
     itſelf
    -0.72
    Дереккөздер
    -0.71
     Савезне
    -0.70
    POSITIVE LOGITS
     IActionResult
    0.47
    baomidou
    0.47
    class
    0.46
     class
    0.45
    roc
    0.45
    qiang
    0.43
    طه
    0.42
     Lop
    0.41
    OF
    0.41
     mio
    0.41
    Activations Density 1.737%

    No Known Activations