© 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. 329
    Prev
    Next
    INDEX
    Explanations

    or

    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
    UnusedPrivate
    -0.83
     &___
    -0.70
    RegistryLite
    -0.69
    AnchorStyles
    -0.63
     PLWABN
    -0.63
    invokeLater
    -0.63
    setVerticalGroup
    -0.62
     autorytatywna
    -0.60
    GraphicsUnit
    -0.59
     NUKAT
    -0.58
    POSITIVE LOGITS
     with
    1.42
     by
    1.38
     from
    0.94
     dengan
    0.92
    with
    0.90
     avec
    0.88
     through
    0.87
     via
    0.78
     WITH
    0.78
     với
    0.74
    Activations Density 0.005%

    No Known Activations