© 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. 0-CLT-HP
    7. 95332
    Prev
    Next
    INDEX
    Explanations

    institutions and molecules

    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
     réguli
    -1.25
     larmes
    -1.23
     lèvres
    -1.12
     feroit
    -1.12
     épaules
    -1.12
     mères
    -1.11
     industriels
    -1.10
     supérieurs
    -1.09
     oreilles
    -1.07
     démocr
    -1.07
    POSITIVE LOGITS
    ization
    0.96
    ized
    0.95
    ity
    0.83
    izing
    0.81
    ists
    0.68
    ize
    0.67
    isation
    0.64
    ism
    0.63
    ist
    0.62
    ITY
    0.61
    Activations Density 0.325%

    No Known Activations