© 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. 1-CLT-HP
    7. 11425
    Prev
    Next
    INDEX
    Explanations

    has have

    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
     particulières
    -0.64
     &___
    -0.59
     استنادى
    -0.57
    ItemBackground
    -0.57
    Искәрмәләр
    -0.57
    脚注の使い方
    -0.56
    MigrationBuilder
    -0.56
    Obrázky
    -0.54
     ujednoznacz
    -0.54
     cardiaque
    -0.54
    POSITIVE LOGITS
     (
    0.71
    tigious
    0.57
     to
    0.55
     mapStateToProps
    0.53
    UnknownFields
    0.51
    ="#">
    0.50
    duled
    0.49
     GetEnumerator
    0.47
    selectAll
    0.47
     %>%
    0.47
    Activations Density 0.005%

    No Known Activations