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. 20-CLT-HP
    4. 74382
    Prev
    Next
    INDEX
    Explanations

    mt

    np_max-act-logits · 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
    i
    -0.56
    ett
    -0.55
    erte
    -0.52
    iest
    -0.51
     Jes
    -0.51
    en
    -0.50
    sted
    -0.50
    er
    -0.50
     AssemblyCompany
    -0.49
    atguigu
    -0.49
    POSITIVE LOGITS
     mères
    0.53
     excès
    0.52
     puissante
    0.50
    ranean
    0.50
     supérieurs
    0.50
     qualités
    0.49
     aveug
    0.48
     mauvaises
    0.47
     commerciales
    0.47
     modificación
    0.47
    Activations Density 0.081%

    No Known Activations