© 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. 1-CLT-HP
    7. 46214
    Prev
    Next
    INDEX
    Explanations

    observe

    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
    :✨
    -0.88
    Tikang
    -0.88
     cherchés
    -0.85
     snippetHide
    -0.84
    HostException
    -0.83
    первых
    -0.83
    UnusedPrivate
    -0.82
     MessageBoxIcon
    -0.81
     Meksiku
    -0.80
    GraphicsUnit
    -0.79
    POSITIVE LOGITS
     ge
    0.44
    ge
    0.43
    軽い
    0.43
    g
    0.42
    common
    0.40
    rance
    0.39
    Common
    0.39
     common
    0.38
    cmd
    0.36
    beforeEach
    0.36
    Activations Density 0.010%

    No Known Activations