© 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. 12040
    Prev
    Next
    INDEX
    Explanations

    begin

    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
     Hauses
    -0.55
     isomers
    -0.50
     translocation
    -0.50
     évêque
    -0.50
    imak
    -0.48
    PyTuple
    -0.48
     rearrangement
    -0.47
     Española
    -0.46
     laziness
    -0.46
    Witam
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.85
    tagext
    0.73
     disambiguazione
    0.72
    ="@+
    0.71
    tagHelperRunner
    0.69
    WaitGroup
    0.68
    '},
    0.57
    ToTensor
    0.57
    principalTable
    0.57
    niająca
    0.57
    Activations Density 0.203%

    No Known Activations