© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14851
    Prev
    Next
    INDEX
    Explanations

    main

    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
    
    -0.71
     ddelweddau
    -0.62
    Архівовано
    -0.54
     thereto
    -0.54
     referrerpolicy
    -0.54
    ogre
    -0.52
     Всё
    -0.51
    tableFuture
    -0.50
    Hozzáférés
    -0.50
    ExtendWith
    -0.50
    POSITIVE LOGITS
    PreferredItem
    0.76
    LookAnd
    0.67
    featureID
    0.53
    ValueGeneration
    0.53
    CloseOperation
    0.52
     newBuilder
    0.52
     <>",
    0.50
     propOrder
    0.49
    bcrypt
    0.49
     Coach
    0.47
    Activations Density 0.006%

    No Known Activations