© 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. 72002
    Prev
    Next
    INDEX
    Explanations

    technical/data context

    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
    UnsafeEnabled
    -0.81
     bezeichneter
    -0.65
    jiny
    -0.62
    ingeki
    -0.62
    Prote
    -0.62
     Prote
    -0.60
    IntoConstraints
    -0.57
    laires
    -0.57
    ontale
    -0.57
     Wikimedijinoj
    -0.56
    POSITIVE LOGITS
    httphttps
    0.62
    WithIOException
    0.54
    addImage
    0.46
    ceso
    0.45
    itos
    0.45
     happened
    0.41
    tios
    0.41
     оригіналу
    0.40
     lies
    0.39
    AdapterFactory
    0.39
    Activations Density 0.001%

    No Known Activations