© 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. 95535
    Prev
    Next
    INDEX
    Explanations

    Chemical and tense topics

    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
    ten
    -0.86
     ten
    -0.82
     conf
    -0.59
     tense
    -0.57
    Ten
    -0.55
     Ten
    -0.52
     res
    -0.52
     eight
    -0.49
    eight
    -0.48
     form
    -0.48
    POSITIVE LOGITS
     Jefus
    0.85
     unknownFields
    0.84
     myſelf
    0.79
     Majefty
    0.77
     iſt
    0.76
     photolibrary
    0.75
     doubtnut
    0.74
     Anſ
    0.73
     Chriftian
    0.73
    TestingModule
    0.70
    Activations Density 0.267%

    No Known Activations