© 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. 92552
    Prev
    Next
    INDEX
    Explanations

    BST

    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
     BST
    -0.93
    BST
    -0.80
     pall
    -0.79
    
    -0.68
    Réalisation
    -0.59
     Majefty
    -0.56
     للاسماء
    -0.56
     perſon
    -0.56
    råd
    -0.52
     neceſſ
    -0.52
    POSITIVE LOGITS
     requestCode
    0.57
    djangoproject
    0.57
    chtenstein
    0.55
    GEBURTSDATUM
    0.55
    oader
    0.54
    setof
    0.52
    مزید
    0.52
     uVar
    0.51
    esModule
    0.50
    erdo
    0.50
    Activations Density 2.602%

    No Known Activations