© 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. 2474
    Prev
    Next
    INDEX
    Explanations

    technical explanations/requirements

    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
     nor
    -1.20
    nor
    -0.98
     anymore
    -0.88
    而是
    -0.85
     Nor
    -0.84
    Nor
    -0.83
    ύτε
    -0.80
     melainkan
    -0.73
     unless
    -0.68
     heller
    -0.64
    POSITIVE LOGITS
     سكانية
    0.71
    Fordítás
    0.66
     Normdatei
    0.62
     ujednoznacz
    0.60
     autorytatywna
    0.59
    anskje
    0.59
     ويكيميديا
    0.57
    IsMutable
    0.57
    annot
    0.56
    StoreMessageInfo
    0.56
    Activations Density 0.032%

    No Known Activations