© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45223
    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
     gra
    -0.50
     ${\
    -0.49
     Jones
    -0.46
     g
    -0.44
     b
    -0.44
     Briggs
    -0.43
     Ben
    -0.42
    ↵
    -0.42
     http
    -0.41
    джан
    -0.41
    POSITIVE LOGITS
    قایناقلار
    0.90
     ་་
    0.88
     propOrder
    0.86
     Efq
    0.83
    IsContent
    0.82
     nahilalakip
    0.81
    Datuak
    0.80
     immédi
    0.77
    DockStyle
    0.77
     vectorielles
    0.77
    Activations Density 1.931%

    No Known Activations