© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94916
    Prev
    Next
    INDEX
    Explanations

    addresses

    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
     addresses
    -1.89
     Addresses
    -1.42
    addresses
    -1.20
     addressed
    -1.15
    Addresses
    -1.09
     adresses
    -1.09
     addressing
    -0.98
     Addressing
    -0.86
    addressed
    -0.86
    Addressing
    -0.79
    POSITIVE LOGITS
     تضيفلها
    0.95
     gynhyrchwyd
    0.91
    Clik
    0.80
     Réponses
    0.80
    writeFieldEnd
    0.79
    mybatisplus
    0.78
     disambiguazione
    0.75
    JspWriter
    0.75
    astify
    0.75
     CreateTagHelper
    0.74
    Activations Density 1.240%

    No Known Activations