© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90662
    Prev
    Next
    INDEX
    Explanations

    angas

    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
     étoient
    -0.68
     avoient
    -0.65
     auroit
    -0.64
     prêtres
    -0.64
     enfans
    -0.63
     feroit
    -0.63
     démocr
    -0.62
     touristes
    -0.61
     quelcon
    -0.60
     bienfaits
    -0.60
    POSITIVE LOGITS
    <bos>
    0.77
     Division
    0.56
    ↵↵
    0.54
    '
    0.54
    IUrlHelper
    0.54
     Victory
    0.53
    [toxicity=0]
    0.53
     Extra
    0.52
    ])));
    0.52
     Gold
    0.51
    Activations Density 0.288%

    No Known Activations