© 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. 5-CLT-HP
    7. 373
    Prev
    Next
    INDEX
    Explanations

    /

    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
     ExecuteAsync
    -0.66
     שוליים
    -0.58
    jooq
    -0.56
     jadx
    -0.53
     سكانية
    -0.53
    CloseOperation
    -0.52
    
    -0.52
    مزید
    -0.52
    SOUNDBITE
    -0.51
     facie
    -0.50
    POSITIVE LOGITS
    庁
    0.56
    WebElementEntity
    0.52
     tungkol
    0.49
    NegativeButton
    0.48
     abuelos
    0.47
    พ
    0.46
    forRoot
    0.46
    exitRule
    0.45
     &___
    0.45
    latz
    0.45
    Activations Density 0.008%

    No Known Activations