© 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. 97032
    Prev
    Next
    INDEX
    Explanations

    languages

    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
     languages
    -2.34
     Languages
    -1.92
    Languages
    -1.46
     Sprachen
    -1.44
    languages
    -1.39
     langues
    -1.34
     idiomas
    -1.17
     lingue
    -1.00
     myſelf
    -0.99
     itſelf
    -0.97
    POSITIVE LOGITS
     ​​
    0.85
     of
    0.65
    .
    0.57
     used
    0.57
    ی
    0.55
     (
    0.54
    ,
    0.53
    ​​
    0.52
     use
    0.51
     
    0.49
    Activations Density 0.051%

    No Known Activations