© 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. 1-CLT-HP
    7. 15711
    Prev
    Next
    INDEX
    Explanations

    these

    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
     prêtres
    -0.47
    woche
    -0.47
    kret
    -0.47
    これらの
    -0.47
    lihood
    -0.46
     pères
    -0.46
     CONCERN
    -0.45
     Tone
    -0.45
     These
    -0.44
    ciety
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.87
     resourceCulture
    0.83
    NameInMap
    0.82
    UnusedPrivate
    0.81
    SharedDtor
    0.80
    Personendaten
    0.79
     <<<<<<<<<<<<<<
    0.78
    GEBURTSDATUM
    0.75
    fjspx
    0.75
    RegistryLite
    0.74
    Activations Density 0.094%

    No Known Activations