© 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. 5-CLT-HP
    7. 94194
    Prev
    Next
    INDEX
    Explanations

    AP

    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
     للمعارف
    -0.66
    APPS
    -0.54
    RESS
    -0.53
    CreateModel
    -0.52
    resses
    -0.52
     spu
    -0.51
     StatelessWidget
    -0.51
     PrintWriter
    -0.51
     Tapatalk
    -0.50
     diſt
    -0.50
    POSITIVE LOGITS
    WireFormat
    0.59
     ComVisible
    0.56
    oredCriteria
    0.53
    RTLD
    0.50
    queryInterface
    0.49
    HideFlags
    0.48
     förs
    0.47
     BytesLike
    0.46
     tajam
    0.45
    temos
    0.44
    Activations Density 0.003%

    No Known Activations