© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78024
    Prev
    Next
    INDEX
    Explanations

    Hump

    np_max-act-logits · 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
    Negative Logits
    ClientSize
    -0.77
    Архівовано
    -0.64
     '\\;'
    -0.62
     &___
    -0.62
     AssemblyTitle
    -0.61
    TagMode
    -0.59
    protoc
    -0.57
    TintMode
    -0.56
    limin
    -0.55
    ::~
    -0.55
    POSITIVE LOGITS
    springer
    0.50
    ersdorf
    0.41
    dhcp
    0.40
    toaster
    0.40
    trout
    0.39
     cooler
    0.38
    ̓
    0.38
     jacks
    0.37
    zyż
    0.37
    itty
    0.37
    Activations Density 0.003%

    No Known Activations