© 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. 91524
    Prev
    Next
    INDEX
    Explanations

    computer/electronic devices

    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
    ximadamente
    -0.59
     ComVisible
    -0.59
     gezet
    -0.56
    moth
    -0.56
    rophi
    -0.56
     rumahnya
    -0.55
     للمعارف
    -0.54
    ropho
    -0.54
    quartered
    -0.54
     שוליים
    -0.54
    POSITIVE LOGITS
     digital
    0.57
    digital
    0.54
    DIPSETTING
    0.54
     ModelExpression
    0.54
    :✨
    0.50
    Data
    0.50
    internet
    0.50
    Information
    0.49
     internet
    0.49
     printer
    0.49
    Activations Density 0.007%

    No Known Activations