© 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. 0-CLT-HP
    7. 41228
    Prev
    Next
    INDEX
    Explanations

    lately

    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
    ,
    -0.71
     lately
    -0.65
     Lately
    -0.63
    /
    -0.56
     (
    -0.51
     or
    -0.50
     the
    -0.48
    ?
    -0.48
    最近は
    -0.48
     Tax
    -0.46
    POSITIVE LOGITS
    Aiheesta
    0.64
    findpost
    0.64
     StatefulWidget
    0.60
     doubtnut
    0.60
    oara
    0.60
    AndPassword
    0.60
    RTLD
    0.59
     Waray
    0.59
    DrawerToggle
    0.59
     crdi
    0.58
    Activations Density 0.223%

    No Known Activations