© 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. 4-CLT-HP
    7. 571
    Prev
    Next
    INDEX
    Explanations

    than

    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
    IVEREF
    -0.88
    NameInMap
    -0.84
    Personendaten
    -0.83
    GEBURTSDATUM
    -0.83
    تقاوى
    -0.82
     betweenstory
    -0.81
     CreateTagHelper
    -0.79
    titleMargin
    -0.78
    ResumeLayout
    -0.75
     Roskov
    -0.75
    POSITIVE LOGITS
     do
    1.09
    do
    0.68
     Do
    0.65
     does
    0.60
    Do
    0.54
     DO
    0.54
     don
    0.52
     perform
    0.51
     include
    0.46
    |$
    0.45
    Activations Density 0.006%

    No Known Activations