© 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. 4-CLT-HP
    7. 2938
    Prev
    Next
    INDEX
    Explanations

    nitric oxide

    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
    PIP
    -0.60
    PEL
    -0.55
     PEL
    -0.54
    таж
    -0.52
    POS
    -0.52
     PIP
    -0.50
    vara
    -0.50
     pip
    -0.50
    erv
    -0.50
    nar
    -0.49
    POSITIVE LOGITS
     Normdatei
    0.74
     wikipagina
    0.62
     désert
    0.59
     håll
    0.58
    pédie
    0.58
    visející
    0.57
    fromnode
    0.55
     maille
    0.53
    TypedDataSet
    0.52
     veckor
    0.52
    Activations Density 0.001%

    No Known Activations