© 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. 0-CLT-HP
    7. 1714
    Prev
    Next
    INDEX
    Explanations

    A

    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
    A
    -1.50
     A
    -1.45
     А
    -0.74
    C
    -0.73
    S
    -0.69
     a
    -0.63
     
    -0.63
    T
    -0.58
    D
    -0.57
    L
    -0.54
    POSITIVE LOGITS
    queous
    0.95
    WriteTagHelper
    0.93
    fraid
    0.90
     Efq
    0.89
    poptosis
    0.87
     Monfieur
    0.87
     ―――――
    0.86
    therosclerosis
    0.84
    ']]
    0.83
    хьтан
    0.82
    Activations Density 0.092%

    No Known Activations