© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97431
    Prev
    Next
    INDEX
    Explanations

    Code/Math

    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
    //</
    -0.50
    gyar
    -0.48
     Мексичка
    -0.47
     trust
    -0.46
    ?,?,
    -0.46
     Bre
    -0.45
     boo
    -0.45
     halte
    -0.45
     sharp
    -0.44
    Хро
    -0.44
    POSITIVE LOGITS
    WireFormatLite
    0.65
     StringTokenizer
    0.57
    RESIST
    0.56
     للاسماء
    0.54
    InjectAttribute
    0.54
     neutrons
    0.53
     RequestMethod
    0.52
     auroit
    0.52
     Maschine
    0.52
    CodedInputStream
    0.52
    Activations Density 0.001%

    No Known Activations