© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97269
    Prev
    Next
    INDEX
    Explanations

    technical analysis

    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
    nos
    -0.84
    posed
    -0.67
    RenderAtEndOf
    -0.63
    nosa
    -0.61
    multer
    -0.53
    Argument
    -0.52
     चीज़ों
    -0.52
     Frost
    -0.50
    rån
    -0.49
     تانيه
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    0.69
    ities
    0.62
    écnicas
    0.60
     Atherton
    0.59
    WithIOException
    0.58
    FTFY
    0.57
    SerializedSize
    0.57
     myſelf
    0.57
     whispers
    0.57
    Abitanti
    0.56
    Activations Density 1.315%

    No Known Activations