© 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. 92761
    Prev
    Next
    INDEX
    Explanations

    Keep

    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
    keep
    -1.03
     Keep
    -0.96
    Keep
    -0.86
    KEEP
    -0.80
     keep
    -0.73
     KEEP
    -0.72
    theless
    -0.71
     détruit
    -0.67
    quelles
    -0.61
    Zeneca
    -0.60
    POSITIVE LOGITS
    <?
    0.73
     it
    0.69
     trying
    0.68
     attempting
    0.63
     examining
    0.62
     analyzing
    0.62
     studying
    0.61
     going
    0.61
     seeking
    0.60
     accessing
    0.60
    Activations Density 0.008%

    No Known Activations