© 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. 40571
    Prev
    Next
    INDEX
    Explanations

    field/property

    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
    group
    -0.47
     sessionFactory
    -0.46
    FromArgb
    -0.44
     Group
    -0.44
    Przypisy
    -0.44
    参考文献
    -0.43
    '
    -0.43
     pra
    -0.43
    BASEPATH
    -0.42
     group
    -0.41
    POSITIVE LOGITS
     Efq
    0.95
     myſelf
    0.84
     pleaſure
    0.80
     itſelf
    0.77
     raiſ
    0.77
    ſelves
    0.73
     themſelves
    0.73
     uſed
    0.73
     houſe
    0.73
     deſt
    0.72
    Activations Density 0.025%

    No Known Activations