© 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. 20-CLT-HP
    4. 74875
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · 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
    Билгалдахарш
    -0.62
     bicchiere
    -0.59
     <<<<<<<<<<<<<<
    -0.57
     figliu
    -0.57
    mybatisplus
    -0.56
     సౌకర్య
    -0.55
    ///</
    -0.55
     réfrig
    -0.53
    angliski
    -0.53
    defaults
    -0.52
    POSITIVE LOGITS
     was
    0.91
    was
    0.85
     Was
    0.80
    Was
    0.80
     WAS
    0.72
     wasps
    0.65
    WAS
    0.62
     wasn
    0.60
     hor
    0.57
     were
    0.56
    Activations Density 0.001%

    No Known Activations