© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2622
    Prev
    Next
    INDEX
    Explanations

    code

    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
    flyer
    -0.46
    ujudkan
    -0.45
    avía
    -0.44
    Démographie
    -0.42
     van
    -0.41
    immediate
    -0.41
     Lat
    -0.40
    uttavia
    -0.39
    prisma
    -0.38
     בן
    -0.38
    POSITIVE LOGITS
    StoryboardSegue
    0.87
    AndEndTag
    0.86
    oredCriteria
    0.83
    esModule
    0.79
    IntoConstraints
    0.77
     beginnetje
    0.76
     <=",
    0.75
    EndInit
    0.72
    invokeLater
    0.69
    UnsafeEnabled
    0.67
    Activations Density 0.001%

    No Known Activations