© 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. 5-CLT-HP
    7. 5817
    Prev
    Next
    INDEX
    Explanations

    archaeological

    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
     estimés
    -0.51
    +#+#
    -0.51
     архивлан
    -0.51
    parsedMessage
    -0.50
    ForValue
    -0.50
    ParseTree
    -0.49
    InputTagHelper
    -0.49
    ArrowToggle
    -0.45
    UpInside
    -0.44
    обре
    -0.44
    POSITIVE LOGITS
     setw
    0.71
     PopupWindow
    0.58
     getArguments
    0.55
     tarko
    0.52
    PhysRev
    0.52
     wonen
    0.51
     väli
    0.50
    Encyklopedia
    0.50
    htiö
    0.50
     missions
    0.49
    Activations Density 0.000%

    No Known Activations