© 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. 4-CLT-HP
    7. 735
    Prev
    Next
    INDEX
    Explanations

    to

    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
    WithIOException
    -0.70
     referenties
    -0.68
    jgl
    -0.67
     dataList
    -0.64
     吋
    -0.61
     betweenstory
    -0.60
     Theſe
    -0.60
     Wicidata
    -0.60
     auroit
    -0.59
     الدولى
    -0.58
    POSITIVE LOGITS
     learn
    0.51
     determine
    0.46
     coar
    0.42
    openzeppelin
    0.42
    rafat
    0.41
    inSlope
    0.41
    znej
    0.40
     hopefully
    0.40
    Addo
    0.40
    chakra
    0.40
    Activations Density 0.003%

    No Known Activations