© 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. 0-CLT-HP
    7. 1304
    Prev
    Next
    INDEX
    Explanations

    Seniors

    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
    ut
    -0.65
    Stars
    -0.62
    WEDNESDAY
    -0.61
     Stars
    -0.60
    PYX
    -0.60
    Thursday
    -0.59
    ingual
    -0.58
    Friday
    -0.57
    THURSDAY
    -0.57
    assador
    -0.56
    POSITIVE LOGITS
    awtextra
    0.67
    /**
    0.59
    PhysRevD
    0.58
    AndEndTag
    0.56
    AsUp
    0.53
    apimachinery
    0.52
    DockStyle
    0.51
     INEC
    0.51
     Voulez
    0.50
     '\\;'
    0.50
    Activations Density 1.590%

    No Known Activations