© 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. 42112
    Prev
    Next
    INDEX
    Explanations

    Molecular

    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
     Molecular
    -0.91
    Molecular
    -0.91
     COVID
    -0.90
    molecular
    -0.90
     molecular
    -0.89
     Covid
    -0.84
    COVID
    -0.83
     covid
    -0.81
    covid
    -0.70
    Covid
    -0.70
    POSITIVE LOGITS
     fubject
    0.63
     duplicates
    0.59
     Shakspeare
    0.59
     itſelf
    0.58
    ſelf
    0.55
    XmlAccessType
    0.55
    fucker
    0.55
    a
    0.55
    httphttps
    0.54
     purpoſe
    0.54
    Activations Density 1.738%

    No Known Activations