© 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. 15003
    Prev
    Next
    INDEX
    Explanations

    moral morality

    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
     moral
    -0.84
    moral
    -0.81
     morality
    -0.80
     Morality
    -0.71
     morals
    -0.71
    Moral
    -0.70
     Moral
    -0.66
    ölkerung
    -0.65
    ofire
    -0.65
     morally
    -0.65
    POSITIVE LOGITS
    AsUp
    0.48
     commissioning
    0.47
     ligiloj
    0.47
     lenker
    0.46
     wrong
    0.45
     utafitiHapana
    0.44
     standing
    0.43
    ServerError
    0.43
     siting
    0.43
     models
    0.42
    Activations Density 0.033%

    No Known Activations