© 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. 92408
    Prev
    Next
    INDEX
    Explanations

    is

    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
    Quiénes
    -0.56
    Czytaj
    -0.53
    Demikian
    -0.51
    HomeAsUpEnabled
    -0.51
    Etimología
    -0.50
     Wikispecies
    -0.50
     worauf
    -0.50
    about
    -0.49
    fellow
    -0.45
    什么是
    -0.45
    POSITIVE LOGITS
    ParallelGroup
    0.80
     المعيارى
    0.72
    AutoField
    0.63
     eligible
    0.59
     allowed
    0.59
    تقاوى
    0.59
     Eligible
    0.58
     Waray
    0.55
     doing
    0.54
    SuccessListener
    0.54
    Activations Density 0.000%

    No Known Activations