© 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. 45459
    Prev
    Next
    INDEX
    Explanations

    lawful

    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
    barrow
    -0.69
     NSCoder
    -0.69
     EconPapers
    -0.67
    chairs
    -0.62
     aastal
    -0.62
     للاسماء
    -0.61
     distanciation
    -0.60
     ligiloj
    -0.59
    🏼
    -0.59
    ếc
    -0.59
    POSITIVE LOGITS
    httphttps
    0.55
    __.__
    0.50
    andExpect
    0.48
     []:
    0.46
    Rv
    0.44
     لينك
    0.44
    ణ
    0.43
     rapid
    0.42
    рев
    0.41
    Rapid
    0.41
    Activations Density 0.025%

    No Known Activations