© 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. 95781
    Prev
    Next
    INDEX
    Explanations

    civil rights and conflicts

    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
     linge
    -0.52
     compréhen
    -0.50
     derechos
    -0.49
     anest
    -0.49
     rayos
    -0.47
     élas
    -0.47
     aktu
    -0.47
    front
    -0.45
     front
    -0.43
     meny
    -0.42
    POSITIVE LOGITS
     Normdatei
    1.13
     itſelf
    0.92
     חיצוניים
    0.85
     pinulongan
    0.82
     bezeichneter
    0.80
     Majefty
    0.80
     intptr
    0.80
    ">//
    0.77
     poffible
    0.77
     Jefus
    0.75
    Activations Density 0.257%

    No Known Activations