© 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. 1-CLT-HP
    7. 950
    Prev
    Next
    INDEX
    Explanations

    traditional/conventional

    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
    LabelTagHelper
    -0.85
     snippetHide
    -0.79
    ंदीखरीदारी
    -0.78
    principalColumn
    -0.71
     consultato
    -0.69
    Personendaten
    -0.68
     AssemblyProduct
    -0.67
    ագրություններ
    -0.67
    Atsauces
    -0.66
     المعرف
    -0.65
    POSITIVE LOGITS
     lab
    0.51
     laboratory
    0.49
    cellation
    0.47
    อร
    0.46
    way
    0.46
    fang
    0.45
    membered
    0.45
    SnackBar
    0.44
    amycin
    0.43
    azole
    0.43
    Activations Density 0.086%

    No Known Activations