© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92795
    Prev
    Next
    INDEX
    Explanations

    visual

    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
     poppies
    -0.58
     betweenstory
    -0.58
    ьаж
    -0.57
     Италијани
    -0.56
     Viena
    -0.56
     Faculté
    -0.55
    Personensuche
    -0.54
     Juárez
    -0.54
     gepubliceerd
    -0.54
     mulberry
    -0.53
    POSITIVE LOGITS
    DataAnnotations
    0.67
    ]")]
    0.67
     <<<<<<<<<<<<<<
    0.63
    ViewImports
    0.57
    发表于
    0.56
    DrawerToggle
    0.56
     Ext
    0.56
    ContentAsync
    0.54
    setupUi
    0.54
     insuffisamment
    0.51
    Activations Density 1.244%

    No Known Activations