© 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. 92602
    Prev
    Next
    INDEX
    Explanations

    mixed content snippets

    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
     Quoted
    -0.68
     télécharge
    -0.58
     Ivo
    -0.57
     verrez
    -0.57
     milo
    -0.56
    ء
    -0.56
     hectáreas
    -0.56
    crossover
    -0.56
     crossover
    -0.54
     Crossover
    -0.54
    POSITIVE LOGITS
     nahilalakip
    0.71
     חיצוניים
    0.69
     INTERESAR
    0.56
    Зноскі
    0.54
    mobileqq
    0.51
    öss
    0.50
     Ngb
    0.50
     kom
    0.50
    ContentAlignment
    0.50
    IVEREF
    0.49
    Activations Density 3.036%

    No Known Activations