© 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. 5-CLT-HP
    7. 90936
    Prev
    Next
    INDEX
    Explanations

    social justice

    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
     FontWeight
    -0.54
    putra
    -0.50
    WebVitals
    -0.48
    ]")]
    -0.47
    🏾
    -0.47
     autorytatywna
    -0.46
    !*\
    -0.44
    Jeografia
    -0.44
     calldata
    -0.43
    🏽
    -0.43
    POSITIVE LOGITS
    protoimpl
    0.62
    BeginContext
    0.60
     étoient
    0.59
     juridiques
    0.58
    }],
    0.56
     démocr
    0.56
    Ety
    0.56
     PDO
    0.55
    routeProvider
    0.55
    titleMargin
    0.54
    Activations Density 0.002%

    No Known Activations