© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45989
    Prev
    Next
    INDEX
    Explanations

    semiconductors

    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
     للمعارف
    -0.54
    entrion
    -0.52
     فريبيس
    -0.51
     demografica
    -0.50
    ActionCreators
    -0.50
    urlpatterns
    -0.50
    <bos>
    -0.49
     rhy
    -0.49
    aurus
    -0.49
     RegExp
    -0.48
    POSITIVE LOGITS
    出版年
    0.70
    oa̍t
    0.52
    UnusedPrivate
    0.50
    RTGC
    0.50
     junction
    0.50
     potential
    0.47
    >())
    0.47
    BufferException
    0.47
     intptr
    0.46
    herself
    0.45
    Activations Density 0.101%

    No Known Activations