© 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. 0-CLT-HP
    7. 95745
    Prev
    Next
    INDEX
    Explanations

    sorry

    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
    Negative Logits
     ATM
    -0.71
    IsContent
    -0.69
     rubbing
    -0.64
     sorry
    -0.62
    AddTagHelper
    -0.60
    stdafx
    -0.60
     smoking
    -0.59
     Majest
    -0.59
     EconPapers
    -0.58
    metz
    -0.57
    POSITIVE LOGITS
    s
    0.61
     Савезне
    0.54
    ship
    0.52
    o
    0.51
    rhosis
    0.47
    ())).
    0.47
    a
    0.45
    shein
    0.45
    testcase
    0.45
    iven
    0.44
    Activations Density 1.667%

    No Known Activations