© 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. 5-CLT-HP
    4. 94882
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
     Normdatei
    -0.81
     étranger
    -0.60
     étrangère
    -0.58
     profondità
    -0.57
    textwidth
    -0.56
     caccia
    -0.55
    isateur
    -0.55
     fatica
    -0.54
     popoli
    -0.54
     accanto
    -0.53
    POSITIVE LOGITS
    transQ
    0.68
     bParam
    0.67
     reliability
    0.62
     crossorigin
    0.57
     reli
    0.56
    extAlignment
    0.55
    ThroughAttribute
    0.54
     विश्वसनीयता
    0.54
    PreferredItem
    0.54
     Савезне
    0.53
    Activations Density 0.005%

    No Known Activations