© 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. 614
    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
     keeping
    -0.81
    keep
    -0.77
     keep
    -0.76
    Keep
    -0.74
     keeps
    -0.65
    KEEP
    -0.65
     Keep
    -0.64
     kept
    -0.63
    keeping
    -0.62
    Keeping
    -0.60
    POSITIVE LOGITS
     comuniques
    0.78
    <bos>
    0.62
     up
    0.57
    ">)</
    0.56
     track
    0.55
    逅
    0.54
    )__
    0.53
    _))
    0.53
     فريبيس
    0.52
    awtextra
    0.52
    Activations Density 0.019%

    No Known Activations