© 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. 94110
    Prev
    Next
    INDEX
    Explanations

    years

    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
     years
    -2.80
     Years
    -2.28
    years
    -2.28
    Years
    -2.25
     YEARS
    -2.25
    YEARS
    -2.02
     decades
    -1.99
     jaren
    -1.88
     yrs
    -1.87
     months
    -1.85
    POSITIVE LOGITS
    .
    0.71
    ,
    0.71
     of
    0.62
    !
    0.61
    '
    0.58
    /
    0.48
    :
    0.48
     (
    0.47
    old
    0.45
    1
    0.44
    Activations Density 0.225%

    No Known Activations