© 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. 38402
    Prev
    Next
    INDEX
    Explanations

    RT

    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
     Reſ
    -0.65
     Diſ
    -0.65
     poffible
    -0.62
     cauſe
    -0.59
     houſe
    -0.59
     ſche
    -0.58
     tranſ
    -0.57
     neceffary
    -0.57
     Houſe
    -0.57
     pleaſure
    -0.57
    POSITIVE LOGITS
     AssemblyCulture
    0.77
     NSCoder
    0.71
    findpost
    0.67
    getMenuInflater
    0.60
    клопе
    0.57
    izr
    0.54
    ASX
    0.53
     تضيفلها
    0.52
    afficheront
    0.50
    msgTypes
    0.50
    Activations Density 0.038%

    No Known Activations