© 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. 4-CLT-HP
    7. 3064
    Prev
    Next
    INDEX
    Explanations

    Copyrights and project names

    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
    Configurer
    -0.58
     Administrativna
    -0.56
     فريبيس
    -0.54
    MLLoader
    -0.50
    )();
    -0.49
    ografija
    -0.49
    ❉
    -0.48
    czo
    -0.47
     management
    -0.47
     minds
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.66
     مشين
    0.56
     BoxDecoration
    0.56
    Tikang
    0.54
     snippetHide
    0.54
    HomeAsUpEnabled
    0.53
     تضيفلها
    0.52
    netinet
    0.51
     <<<<<<<<<<<<<<
    0.50
    новништво
    0.49
    Activations Density 0.041%

    No Known Activations