© 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. 95560
    Prev
    Next
    INDEX
    Explanations

    Administrator

    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
    ment
    -0.53
    ful
    -0.52
    man
    -0.51
    ments
    -0.47
    s
    -0.42
     grounded
    -0.42
     of
    -0.42
    men
    -0.41
    mer
    -0.41
    way
    -0.40
    POSITIVE LOGITS
     themſelves
    1.01
     myſelf
    1.00
     ſeveral
    1.00
     resourceCulture
    0.97
     itſelf
    0.97
    بوابة
    0.96
     perfons
    0.96
     poffe
    0.95
     poffible
    0.94
     Efq
    0.93
    Activations Density 1.593%

    No Known Activations