© 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. 1-CLT-HP
    7. 15640
    Prev
    Next
    INDEX
    Explanations

    societal structure

    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
    Portale
    -0.66
    <()>
    -0.59
    enderror
    -0.59
    zzleHttp
    -0.57
    AssignableFrom
    -0.57
    stateProvider
    -0.56
    AddTagHelper
    -0.56
    addGroup
    -0.55
    رشف
    -0.55
    RRect
    -0.55
    POSITIVE LOGITS
     externi
    0.60
    ally
    0.54
     Réponses
    0.51
     ExecuteAsync
    0.47
     OBJECTIVE
    0.47
    WSGI
    0.47
    Realm
    0.47
    Datuak
    0.47
     sil
    0.45
    h
    0.45
    Activations Density 0.012%

    No Known Activations