Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39750
    Prev
    Next
    INDEX
    Explanations

    flying

    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
     Efq
    -0.97
     ―――――
    -0.93
    iffance
    -0.91
    ]<<"
    -0.90
     AppColors
    -0.90
     Theſe
    -0.87
     chré
    -0.85
    InjectAttribute
    -0.84
    berdayakan
    -0.83
     ainfi
    -0.82
    POSITIVE LOGITS
    to
    0.66
    e
    0.65
    a
    0.57
    de
    0.55
    in
    0.54
    en
    0.54
    ↵↵
    0.52
    t
    0.52
     in
    0.50
    nt
    0.49
    Activations Density 0.151%

    No Known Activations