© 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. 73169
    Prev
    Next
    INDEX
    Explanations

    various text sources

    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
     ané
    -0.54
    ıyordu
    -0.53
    openg
    -0.53
     %{
    -0.53
     viewDidLoad
    -0.53
     externi
    -0.52
    rceil
    -0.52
    IsContent
    -0.52
    lessness
    -0.50
     Vee
    -0.50
    POSITIVE LOGITS
    calar
    0.57
    UnsafeEnabled
    0.51
    codiles
    0.49
    queryInterface
    0.48
    HasForeignKey
    0.47
    imals
    0.47
    fillType
    0.46
    setCellValue
    0.46
    ագրություններ
    0.45
    достатки
    0.44
    Activations Density 0.000%

    No Known Activations