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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38248
    Prev
    Next
    INDEX
    Explanations

    harm, damage

    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
    idea
    -0.54
     copolymer
    -0.52
     Damage
    -0.51
     laterale
    -0.50
     lavage
    -0.49
     Idea
    -0.48
     Damages
    -0.48
     damage
    -0.48
     impractica
    -0.48
    tip
    -0.47
    POSITIVE LOGITS
     propOrder
    0.84
     HasFactory
    0.75
    #+#
    0.72
    brainly
    0.72
    MigrationBuilder
    0.72
    Diweddarwch
    0.71
    ItemBackground
    0.71
    بوابة
    0.69
     snippetHide
    0.68
    ंदीखरीदारी
    0.68
    Activations Density 0.048%

    No Known Activations