© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4804
    Prev
    Next
    INDEX
    Explanations

    do

    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
     resourceCulture
    -0.71
    dentes
    -0.63
     Bones
    -0.54
    setIcon
    -0.54
    endpush
    -0.52
    emplos
    -0.52
     Tinker
    -0.51
    jego
    -0.50
    ində
    -0.50
    فر
    -0.49
    POSITIVE LOGITS
    WriteTagHelper
    0.57
    ]-->
    0.51
    weetened
    0.49
    DockStyle
    0.47
    GMENT
    0.47
     propOrder
    0.46
     FormsModule
    0.46
    ="%
    0.44
    BeginContext
    0.44
    Rptr
    0.44
    Activations Density 0.002%

    No Known Activations