© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14050
    Prev
    Next
    INDEX
    Explanations

    loop

    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
    Loop
    -1.11
    loop
    -1.08
     Loop
    -1.01
     loop
    -0.98
     LOOP
    -0.95
     Loops
    -0.89
    LOOP
    -0.82
    loops
    -0.78
     loops
    -0.77
    Loops
    -0.69
    POSITIVE LOGITS
    AndEndTag
    0.91
    +:+
    0.82
    UnitTesting
    0.67
    GOTREF
    0.66
    medriver
    0.63
    انجليز
    0.62
     AssemblyVersion
    0.62
    imageshack
    0.61
    كويكب
    0.61
    invokeLater
    0.61
    Activations Density 0.051%

    No Known Activations