© 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. 14413
    Prev
    Next
    INDEX
    Explanations

    Nuclear accidents/power plants

    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
    elemField
    -0.76
    addCriterion
    -0.75
     defaultstate
    -0.70
    djangoproject
    -0.70
     GenerationType
    -0.66
     незавершена
    -0.60
    AnchorTagHelper
    -0.58
     resourceCulture
    -0.57
    حياتها
    -0.57
    PreferredItem
    -0.56
    POSITIVE LOGITS
     GoogleFonts
    0.56
     gravy
    0.53
     betweenstory
    0.47
    Composable
    0.47
    Minerals
    0.47
     minerals
    0.46
     Colonia
    0.46
     verbs
    0.45
     oprot
    0.44
     <<<<<<<<<<<<<<
    0.44
    Activations Density 0.023%

    No Known Activations