© 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. 43288
    Prev
    Next
    INDEX
    Explanations

    requirement

    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
     CreateTagHelper
    -1.02
     EconPapers
    -0.75
     requirement
    -0.71
     requiring
    -0.71
    Personensuche
    -0.66
    expandindo
    -0.66
    
    -0.66
     required
    -0.66
     Exacts
    -0.63
    XmlEnum
    -0.62
    POSITIVE LOGITS
     Flat
    0.51
    ddha
    0.49
    InstanceState
    0.49
    堅
    0.47
    Flat
    0.47
    ieri
    0.47
     ressource
    0.46
     Draht
    0.46
    pol
    0.46
    快
    0.46
    Activations Density 0.674%

    No Known Activations