© 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. 5-CLT-HP
    7. 94206
    Prev
    Next
    INDEX
    Explanations

    1

    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
     AssemblyCompany
    -0.57
    WebVitals
    -0.57
    ρίς
    -0.51
    skosten
    -0.51
     extras
    -0.50
    InvalidProtocol
    -0.49
     Letras
    -0.49
     explanatory
    -0.49
    BrowserModule
    -0.48
     humanity
    -0.48
    POSITIVE LOGITS
    MessageOf
    0.64
    RenderAtEndOf
    0.56
    DrawerToggle
    0.56
     mergeFrom
    0.52
     estimés
    0.50
     Geraadpleegd
    0.50
    TestTools
    0.49
     OMITBAD
    0.48
     cherchés
    0.47
     الحره
    0.45
    Activations Density 0.001%

    No Known Activations