© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 604
    Prev
    Next
    INDEX
    Explanations

    world

    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
    StoryboardSegue
    -0.87
    ValueStyle
    -0.80
    urlpatterns
    -0.70
     متعلقه
    -0.68
     mapStateToProps
    -0.67
     Nacionales
    -0.66
     myſelf
    -0.64
     useSelector
    -0.63
     RoutedEventArgs
    -0.63
     useDispatch
    -0.62
    POSITIVE LOGITS
    migrationBuilder
    0.47
    >//
    0.46
     something
    0.42
     SwitchCompat
    0.41
     things
    0.41
     thing
    0.40
     чему
    0.39
    te
    0.39
    cerne
    0.38
     anf
    0.38
    Activations Density 0.001%

    No Known Activations