© 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. 5519
    Prev
    Next
    INDEX
    Explanations

    Software and code

    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
    addPreferredGap
    -0.52
    
    -0.49
     verzichten
    -0.41
    InjectMocks
    -0.40
    ///</
    -0.40
    titleMargin
    -0.38
    '])->
    -0.38
     AssemblyVersion
    -0.36
     tất
    -0.36
    autant
    -0.36
    POSITIVE LOGITS
    Autoritní
    0.86
    StoryboardSegue
    0.76
     становника
    0.72
     خارجية
    0.71
    íncia
    0.70
     MessageBoxIcon
    0.70
    kháu
    0.69
     kasarigan
    0.68
    googleapis
    0.67
    Smarty
    0.67
    Activations Density 0.006%

    No Known Activations