© 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. 92098
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     pauv
    -0.52
    Diwedd
    -0.45
    utilisons
    -0.45
     spese
    -0.44
    Nice
    -0.44
    nice
    -0.43
     OFDb
    -0.42
    known
    -0.42
    onomía
    -0.41
     Савезне
    -0.41
    POSITIVE LOGITS
     other
    0.77
     if
    0.70
    ؤلاء
    0.65
     ever
    0.65
     OTHER
    0.63
     sometimes
    0.63
     eternally
    0.61
    migrationBuilder
    0.60
     often
    0.59
     infinitely
    0.59
    Activations Density 0.001%

    No Known Activations