© 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. 72860
    Prev
    Next
    INDEX
    Explanations

    statistics and research

    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
    BufferException
    -0.73
    RegistryLite
    -0.70
     NSCoder
    -0.69
    WriteTagHelper
    -0.68
    Демографія
    -0.68
     GoogleFonts
    -0.67
    évaluateur
    -0.66
     InputDecoration
    -0.66
    GEBURTSDATUM
    -0.64
    下载附件
    -0.62
    POSITIVE LOGITS
     Wick
    0.48
    adden
    0.45
     PWN
    0.43
    oura
    0.43
     esternos
    0.42
    Бахар
    0.42
     Winding
    0.41
    ymas
    0.40
    UMBIA
    0.40
     muros
    0.40
    Activations Density 0.001%

    No Known Activations