© 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. 5-CLT-HP
    7. 93947
    Prev
    Next
    INDEX
    Explanations

    of

    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
     EconPapers
    -0.85
     Majefty
    -0.78
    ьаж
    -0.75
    onAttach
    -0.75
     Efq
    -0.74
    IUrlHelper
    -0.73
     feroit
    -0.73
     auroit
    -0.71
     Normdatei
    -0.70
     Monfieur
    -0.70
    POSITIVE LOGITS
     this
    0.71
     This
    0.56
    This
    0.54
    this
    0.52
    .
    0.47
     hereto
    0.46
     below
    0.44
    :
    0.44
     questo
    0.44
     :
    0.43
    Activations Density 0.047%

    No Known Activations