© 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. 20-CLT-HP
    7. 74672
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    WebElementEntity
    -0.69
     Hat
    -0.54
     EconPapers
    -0.54
    (!__
    -0.50
    Hat
    -0.50
    itse
    -0.49
    évaluateur
    -0.48
     Green
    -0.48
    jewództ
    -0.48
     Tahu
    -0.47
    POSITIVE LOGITS
     course
    0.58
     Course
    0.54
     kasarigan
    0.52
    Tikang
    0.51
    Course
    0.51
     fine
    0.51
    Risultati
    0.50
    detectChanges
    0.50
     onOptions
    0.50
    course
    0.49
    Activations Density 0.001%

    No Known Activations