© 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. 0-CLT-HP
    7. 94001
    Prev
    Next
    INDEX
    Explanations

    hate

    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
     promote
    -1.16
     promoting
    -1.11
    Promoting
    -1.07
    promoting
    -1.04
     promotes
    -1.03
    promote
    -1.01
     Promoting
    -0.98
     hate
    -0.88
    Promote
    -0.86
     Promote
    -0.83
    POSITIVE LOGITS
     itſelf
    0.90
     myſelf
    0.82
     pleaſure
    0.81
     reaſon
    0.78
     themſelves
    0.71
     Diſ
    0.70
     Inſ
    0.69
    ſelf
    0.69
    webElementXpaths
    0.69
     ſec
    0.68
    Activations Density 0.401%

    No Known Activations