© 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. 14542
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    WebElementEntity
    -0.64
    PhysRevD
    -0.63
    VIAF
    -0.61
    Autoritní
    -0.58
    ablen
    -0.56
     kasarigan
    -0.54
    Oise
    -0.53
     Artículos
    -0.52
    Historique
    -0.52
    setViewportView
    -0.51
    POSITIVE LOGITS
     للمعارف
    0.74
     تانيه
    0.72
     وتسجيلات
    0.59
     ujednoznacz
    0.59
    rawDesc
    0.59
    нибудь
    0.56
    \{\\
    0.53
     minOccurs
    0.52
    例句
    0.52
     createContext
    0.50
    Activations Density 0.417%

    No Known Activations