© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71600
    Prev
    Next
    INDEX
    Explanations

    Time in hours

    np_max-act-logits · 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
    urlpatterns
    -0.48
     Bourgoin
    -0.47
     ioutil
    -0.47
    ientôt
    -0.47
    curities
    -0.46
    省市镇
    -0.46
    HasBeenSet
    -0.46
    ruct
    -0.46
     <>",
    -0.45
    ïc
    -0.44
    POSITIVE LOGITS
    h
    0.84
     hours
    0.78
    hr
    0.72
     h
    0.71
    hrs
    0.69
     hrs
    0.68
     hr
    0.68
    :
    0.66
    verwijspagina
    0.65
     horas
    0.64
    Activations Density 0.005%

    No Known Activations