© 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. 5-CLT-HP
    7. 91938
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    AntiForgeryToken
    -0.68
    IDENTAL
    -0.57
    Marshaller
    -0.52
    bbene
    -0.52
    )$/,
    -0.50
     Vikipedi
    -0.49
    ScopeManager
    -0.48
    ēl
    -0.48
     sû
    -0.48
     answered
    -0.47
    POSITIVE LOGITS
    tvguidetime
    0.64
     <<<<<<<<<<<<<<
    0.60
    Gambas
    0.59
    ClientRect
    0.54
    Captor
    0.53
    esgue
    0.53
    出版年
    0.52
     configureStore
    0.52
     createState
    0.51
    LookAnd
    0.51
    Activations Density 0.040%

    No Known Activations