© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46179
    Prev
    Next
    INDEX
    Explanations

    around

    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
     réguli
    -0.62
     vectorielle
    -0.59
     policiales
    -0.58
     engraçadas
    -0.55
     normaux
    -0.54
     avoient
    -0.53
     enfans
    -0.53
     solides
    -0.52
     extérieures
    -0.52
    rededor
    -0.51
    POSITIVE LOGITS
     calendriers
    0.74
    BeginContext
    0.66
    Gön
    0.65
    новништво
    0.64
     invokingState
    0.63
    CodeAttribute
    0.63
     '\\;'
    0.61
     BrowserModule
    0.60
     RoutedEventArgs
    0.60
    bolite
    0.59
    Activations Density 0.325%

    No Known Activations