© 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. 94482
    Prev
    Next
    INDEX
    Explanations

    someone saying something

    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
    cách
    -0.51
    имущества
    -0.48
    OfYear
    -0.48
    Modèle
    -0.47
    AudioManager
    -0.47
    $_['
    -0.47
    Lycka
    -0.47
     Frontal
    -0.46
    abstractmethod
    -0.46
    ULTY
    -0.45
    POSITIVE LOGITS
    الحياه
    0.71
    WaitGroup
    0.65
     that
    0.64
    AddTagHelper
    0.62
    appa
    0.56
     almost
    0.54
    kegaard
    0.53
     gainera
    0.52
    WithMany
    0.52
     such
    0.51
    Activations Density 0.006%

    No Known Activations