© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9909
    Prev
    Next
    INDEX
    Explanations

    discrimination

    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
    Not in Any Lists

    No Comments

    Negative Logits
     discrimination
    -0.66
    discrimination
    -0.66
     discriminatory
    -0.57
     Discrimination
    -0.57
    CrossRef
    -0.45
    WebVitals
    -0.44
     שוליים
    -0.43
    вара
    -0.43
    gh
    -0.42
    vara
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.71
    ⓧ
    0.67
    Personendaten
    0.67
     recevez
    0.65
    Rhestr
    0.64
     initWithFrame
    0.63
    parsedMessage
    0.61
     <<<<<<<<<<<<<<
    0.60
    vdash
    0.59
    WebControls
    0.59
    Activations Density 0.017%

    No Known Activations