© 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. 5-CLT-HP
    7. 93099
    Prev
    Next
    INDEX
    Explanations

    nuclear disasters

    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
    Geplaatst
    -0.49
    MigrationBuilder
    -0.45
    ⓧ
    -0.43
     pinulongan
    -0.42
     JADX
    -0.41
    ArrowToggle
    -0.40
     iload
    -0.39
     treo
    -0.38
    tu
    -0.38
    vos
    -0.37
    POSITIVE LOGITS
     BoxFit
    0.66
     cleanup
    0.63
     clean
    0.63
     radioactive
    0.62
     fishing
    0.61
     Fishing
    0.59
     nuclear
    0.58
     decontamination
    0.57
    zboi
    0.57
     metav
    0.57
    Activations Density 0.000%

    No Known Activations