© 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. 5-CLT-HP
    7. 98057
    Prev
    Next
    INDEX
    Explanations

    courthouse/hall

    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
    bindParam
    -0.52
     cooperate
    -0.48
    cologist
    -0.48
     betre
    -0.47
    ViewFeatures
    -0.47
     Réponses
    -0.45
     sleepers
    -0.44
    grub
    -0.44
    วัด
    -0.44
     sams
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    SequentialGroup
    0.69
    Diweddarwch
    0.60
    Datuak
    0.60
     resourceCulture
    0.59
    
    0.58
    LLocation
    0.57
    istoitu
    0.57
     cref
    0.57
    Демографія
    0.57
    Activations Density 0.009%

    No Known Activations