Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 646
    Prev
    Next
    INDEX
    Explanations

    uscular/nth

    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
    uscular
    -1.80
    ])]
    -0.43
     recevrez
    -0.40
     députés
    -0.40
    خواندن
    -0.39
    cú
    -0.39
    ļi
    -0.39
     try
    -0.38
    ьаж
    -0.37
    openzeppelin
    -0.37
    POSITIVE LOGITS
     itſelf
    0.71
    XmlType
    0.71
    Portail
    0.70
     Drapeau
    0.63
     initComponents
    0.62
    principalTable
    0.61
     InputDecoration
    0.60
    GOTREF
    0.60
    InputBorder
    0.60
    AccessorTable
    0.59
    Activations Density 0.681%

    No Known Activations