© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13027
    Prev
    Next
    INDEX
    Explanations

    bing

    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
    entation
    -0.81
    bing
    -0.66
    Enllaces
    -0.53
     calcetines
    -0.51
     Baillargeon
    -0.50
     rayures
    -0.49
    مصادر
    -0.48
     становника
    -0.47
     Romains
    -0.46
    перь
    -0.45
    POSITIVE LOGITS
     noqa
    0.80
    ParallelGroup
    0.66
    IActionResult
    0.65
    ècie
    0.62
     Theſe
    0.57
     للمعارف
    0.57
    LayoutStyle
    0.56
    picasso
    0.56
    iconCls
    0.55
     Anſ
    0.55
    Activations Density 0.096%

    No Known Activations