© 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. 94389
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/names

    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
     itſelf
    -1.03
     myſelf
    -0.94
     Monfieur
    -0.94
     ſeveral
    -0.94
     photolibrary
    -0.93
     themſelves
    -0.92
     Efq
    -0.90
     Shakspeare
    -0.88
     Houſe
    -0.88
     pngtree
    -0.87
    POSITIVE LOGITS
    heits
    0.48
     re
    0.44
    kset
    0.44
    けると
    0.44
     ré
    0.44
    tores
    0.43
    ?
    0.42
     I
    0.42
    manjaro
    0.42
     no
    0.41
    Activations Density 0.554%

    No Known Activations