© 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. 5-CLT-HP
    7. 97671
    Prev
    Next
    INDEX
    Explanations

    Describing a process

    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
     <>",
    -0.72
    PerformLayout
    -0.71
    piram
    -0.66
    تقاوى
    -0.59
    webElementXpaths
    -0.57
    MessageOf
    -0.56
    fromnode
    -0.56
     OFDb
    -0.56
     OMITBAD
    -0.56
    ----</
    -0.55
    POSITIVE LOGITS
     apparent
    0.57
    apparent
    0.56
     Apparent
    0.51
    available
    0.50
     aparente
    0.45
    gameserver
    0.45
     Appears
    0.45
    olerance
    0.44
     available
    0.44
     Determination
    0.43
    Activations Density 0.001%

    No Known Activations