© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 2051
    Prev
    Next
    INDEX
    Explanations

    depressive

    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
    ſelves
    -0.88
     itſelf
    -0.87
    ſelf
    -0.84
     Efq
    -0.78
     myſelf
    -0.76
    neſs
    -0.73
     ſever
    -0.72
     houſe
    -0.72
     neceff
    -0.72
     purpoſe
    -0.72
    POSITIVE LOGITS
    SourceChecksum
    0.73
     للاسماء
    0.51
    mb
    0.51
    ReusableCell
    0.50
     trovar
    0.49
     Plant
    0.48
     litté
    0.48
    CppMethod
    0.48
    leetcode
    0.48
     réunis
    0.47
    Activations Density 1.929%

    No Known Activations