© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93352
    Prev
    Next
    INDEX
    Explanations

    harm

    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
     harm
    -1.79
     harms
    -1.27
    harm
    -1.25
     Harm
    -1.24
     harmed
    -1.23
     harming
    -1.10
     harmful
    -1.09
     hurt
    -1.05
    Harm
    -0.93
    harmed
    -0.82
    POSITIVE LOGITS
    Попис
    0.73
    fully
    0.67
    WriteTagHelper
    0.49
    entine
    0.45
    itinéraire
    0.45
    fulness
    0.44
    ful
    0.44
     pageContext
    0.44
     conviene
    0.44
    enames
    0.43
    Activations Density 1.753%

    No Known Activations