© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45627
    Prev
    Next
    INDEX
    Explanations

    mos

    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
     bocca
    -0.52
     bailarina
    -0.42
     universitarios
    -0.42
     étro
    -0.41
     nationales
    -0.41
    éhez
    -0.41
     religieuses
    -0.40
     svar
    -0.40
     bandeira
    -0.40
     bambino
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    1.02
     EconPapers
    0.91
    webElementXpaths
    0.90
    ]")]
    0.87
    ValueStyle
    0.83
     Réponses
    0.82
     ExecuteAsync
    0.81
    DockStyle
    0.79
    IntoConstraints
    0.78
    </thead>
    0.77
    Activations Density 0.217%

    No Known Activations