© 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. 390
    Prev
    Next
    INDEX
    Explanations

    Great Britain and/or Ireland

    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
    StoryboardSegue
    -0.85
     supérieures
    -0.83
     démocr
    -0.82
     Савезне
    -0.81
     complètes
    -0.81
     supérieurs
    -0.79
     femininas
    -0.79
     dieux
    -0.77
     Paglinawan
    -0.76
     giapp
    -0.75
    POSITIVE LOGITS
    AutoScaleMode
    0.50
     non
    0.40
    AddRange
    0.39
    simpleType
    0.39
     pure
    0.39
    ADELPHIA
    0.39
    dersfield
    0.39
    prepareStatement
    0.39
    twimg
    0.37
    ירו
    0.36
    Activations Density 0.017%

    No Known Activations