© 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. 122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     مواليد
    -0.67
    qtype
    -0.48
     betweenstory
    -0.48
     newBuilder
    -0.47
    }}}
    -0.47
    SharedCtor
    -0.45
     ench
    -0.45
    ặ
    -0.44
     provision
    -0.43
     Réponses
    -0.43
    POSITIVE LOGITS
     coscienza
    0.73
     juridiques
    0.68
     consommateurs
    0.68
    ScopeManager
    0.67
     chrétiens
    0.66
     financières
    0.65
     producteurs
    0.62
     vectorielles
    0.62
    gående
    0.60
     vermelhas
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.