© 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. 97295
    Prev
    Next
    INDEX
    Explanations

    network hosts and traffic

    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
    fjspx
    -0.88
    abestanden
    -0.86
    makeText
    -0.77
     мәкал
    -0.77
     nahilalakip
    -0.75
     propOrder
    -0.75
    featureID
    -0.75
    Personendaten
    -0.74
     CURIAM
    -0.73
     "..\..\
    -0.71
    POSITIVE LOGITS
     vary
    0.63
    yce
    0.57
     myſelf
    0.54
     varier
    0.52
    kez
    0.51
     VPC
    0.50
     varies
    0.50
    tilus
    0.50
     propagated
    0.50
    ſelf
    0.49
    Activations Density 0.237%

    No Known Activations