© 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. 15008
    Prev
    Next
    INDEX
    Explanations

    conflict, danger, negativity

    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
     faction
    -1.96
     factions
    -1.48
    faction
    -1.48
     Faction
    -1.41
    Faction
    -1.20
     Paglinawan
    -0.60
     lèvres
    -0.56
    fraction
    -0.56
     fondament
    -0.54
     quedo
    -0.54
    POSITIVE LOGITS
    GraphicsUnit
    0.69
    ClientSize
    0.64
     Chwiliwch
    0.60
    contentLoaded
    0.58
    
    0.57
    ed
    0.56
    mobileqq
    0.56
    SupportActionBar
    0.54
    enterOuterAlt
    0.53
     EconPapers
    0.53
    Activations Density 0.027%

    No Known Activations