© 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. 20-CLT-HP
    7. 73194
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.61
    styleType
    -0.58
     surla
    -0.55
     addSubview
    -0.50
    InitVars
    -0.49
     OSError
    -0.48
     JADX
    -0.46
     الذات
    -0.44
    readAs
    -0.44
     autorytatywna
    -0.44
    POSITIVE LOGITS
    Liên
    0.49
    Nuorodos
    0.49
     Guillermo
    0.49
    aluc
    0.48
     Exactos
    0.47
    SqlQuery
    0.47
     Gutiérrez
    0.46
     Ganga
    0.46
     exempel
    0.46
    holding
    0.46
    Activations Density 0.000%

    No Known Activations