© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45530
    Prev
    Next
    INDEX
    Explanations

    Cir/cDNA

    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
    Datuak
    -1.17
    tagHelperRunner
    -1.14
    ValueStyle
    -0.95
     resourceCulture
    -0.88
     wireType
    -0.85
    /*
    -0.81
    ]--;
    -0.81
    UnitTesting
    -0.81
    +#+#
    -0.79
     CreateTagHelper
    -0.79
    POSITIVE LOGITS
    san
    0.57
    s
    0.55
    spesies
    0.52
    sun
    0.50
     különböz
    0.49
    ship
    0.49
    snprintf
    0.47
    shell
    0.47
     történ
    0.47
    sm
    0.46
    Activations Density 1.737%

    No Known Activations