© 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. 92471
    Prev
    Next
    INDEX
    Explanations

    una

    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
    una
    -1.05
    UNA
    -0.56
     Doubles
    -0.52
     ioutil
    -0.50
    INSEE
    -0.49
     Forder
    -0.49
    doubles
    -0.48
     SqlDbType
    -0.48
     unan
    -0.48
     doubles
    -0.48
    POSITIVE LOGITS
     незавершена
    0.69
     الرياضيه
    0.66
     thiệu
    0.65
    stdafx
    0.57
     autorytatywna
    0.56
    XmlAccessorType
    0.56
    Naissance
    0.55
    jsxFileName
    0.54
    httphttps
    0.54
    memberof
    0.53
    Activations Density 0.071%

    No Known Activations