© 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. 0-CLT-HP
    7. 42877
    Prev
    Next
    INDEX
    Explanations

    Examining, trying to understand

    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
     originais
    -0.54
    BeginInit
    -0.54
     bienvenue
    -0.53
     löyty
    -0.52
     circulación
    -0.51
    去吧
    -0.49
    îtra
    -0.48
     cáps
    -0.48
     színes
    -0.47
     opdracht
    -0.47
    POSITIVE LOGITS
     its
    0.68
    EDEFAULT
    0.64
    UnitTesting
    0.64
    aarrggbb
    0.60
    complexContent
    0.60
    ølge
    0.56
     الحره
    0.55
     Its
    0.54
    zenio
    0.54
     close
    0.54
    Activations Density 0.058%

    No Known Activations