© 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. 5937
    Prev
    Next
    INDEX
    Explanations

    regions

    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
    principalTable
    -0.57
    Lähteet
    -0.56
    setVerticalGroup
    -0.46
    #}
    -0.45
    ImageContext
    -0.45
     fiel
    -0.44
    ={({
    -0.44
    JspWriter
    -0.44
    "])
    -0.44
    ++]=
    -0.43
    POSITIVE LOGITS
     églises
    0.73
    bentar
    0.67
     Oppen
    0.61
     vérit
    0.59
     visiteurs
    0.54
     cérami
    0.53
    berton
    0.52
     hjemme
    0.52
    izzati
    0.52
    iedy
    0.51
    Activations Density 0.001%

    No Known Activations