© 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. 93577
    Prev
    Next
    INDEX
    Explanations

    Chemical bonds/exchanges

    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
     Iron
    -0.79
     iron
    -0.78
    Iron
    -0.77
     IRON
    -0.61
    iron
    -0.60
    unnitel
    -0.60
    Amicalement
    -0.55
    IRON
    -0.54
     EC
    -0.53
     ModelExpression
    -0.52
    POSITIVE LOGITS
    PYX
    0.59
     Réponses
    0.56
    tagHelperRunner
    0.54
     intptr
    0.53
     ReSharper
    0.52
     LUMP
    0.51
     ganado
    0.49
     Vikipedi
    0.49
    hyrchwyd
    0.49
    oblastoma
    0.48
    Activations Density 0.195%

    No Known Activations