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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 41563
    Prev
    Next
    INDEX
    Explanations

    airways

    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
    castle
    -0.75
    ness
    -0.68
     Guidelines
    -0.65
    dale
    -0.64
    estine
    -0.63
     ""
    
    -0.62
    rum
    -0.60
    ens
    -0.59
    room
    -0.57
    stan
    -0.57
    POSITIVE LOGITS
     Réponses
    0.78
    WithIOException
    0.72
     препратки
    0.67
    setupUi
    0.60
     дописавши
    0.60
     lenker
    0.59
     rapporti
    0.56
    úsqueda
    0.56
    теризу
    0.55
    Pratique
    0.55
    Activations Density 1.830%

    No Known Activations