© 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. 1-CLT-HP
    7. 793
    Prev
    Next
    INDEX
    Explanations

    ku

    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
    PathVariable
    -0.53
     ||
    -0.52
    AttributeSet
    -0.52
     Streak
    -0.51
     bedroom
    -0.50
     fans
    -0.49
    rawtypes
    -0.48
    opha
    -0.48
    romolecules
    -0.48
     blow
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.76
    BeginInit
    0.73
     varandra
    0.70
    ectl
    0.61
     gratuitas
    0.61
     gouvernements
    0.60
     féminine
    0.60
    ))->
    0.60
    脚注の使い方
    0.59
    存于互联网档案馆
    0.58
    Activations Density 0.006%

    No Known Activations