© 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. 416
    Prev
    Next
    INDEX
    Explanations

    secret

    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
     հղումներ
    -0.58
     ambientale
    -0.56
     eens
    -0.52
     sahiptir
    -0.50
    gway
    -0.49
     OMITBAD
    -0.49
     retrô
    -0.48
     irré
    -0.48
    دانشنامهٔ
    -0.48
     ír
    -0.47
    POSITIVE LOGITS
     ingredient
    0.54
     sauce
    0.54
    ViewChild
    0.52
    ศาสตร์
    0.51
     CommonModule
    0.51
     Sauce
    0.50
    mockMvc
    0.50
     Life
    0.50
     power
    0.49
    EndProject
    0.48
    Activations Density 0.002%

    No Known Activations