© 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. 2288
    Prev
    Next
    INDEX
    Explanations

    rounds

    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
     grade
    -0.45
    Personendaten
    -0.44
    grau
    -0.42
    UCION
    -0.42
    WriteTagHelper
    -0.41
     herv
    -0.41
    enderal
    -0.41
     Seni
    -0.40
    mobileqq
    -0.40
    stree
    -0.39
    POSITIVE LOGITS
    PyExc
    0.60
     вікі
    0.59
     OFDb
    0.58
    UrlResolution
    0.57
     terecht
    0.56
    ścioła
    0.54
     kasarigan
    0.53
     gebou
    0.53
    السكان
    0.52
    expandindo
    0.52
    Activations Density 0.002%

    No Known Activations