© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42309
    Prev
    Next
    INDEX
    Explanations

    time periods and days

    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
    ſelf
    -1.08
     itſelf
    -1.02
     ſmall
    -1.01
     raiſ
    -1.00
     pleaſure
    -1.00
     purpoſe
    -0.97
     ſeveral
    -0.96
     months
    -0.96
    neſs
    -0.96
     faſt
    -0.96
    POSITIVE LOGITS
    (
    0.59
    (/
    0.50
    [
    0.49
    l
    0.48
     ("
    0.45
    v
    0.45
    =
    0.45
    ad
    0.45
    ta
    0.43
    pr
    0.42
    Activations Density 0.025%

    No Known Activations