© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    find

    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
    PasswordEncoder
    -0.59
    Latest
    -0.58
     latest
    -0.57
     peine
    -0.57
    ">+
    -0.56
    latest
    -0.55
    most
    -0.55
     Almost
    -0.55
     Latest
    -0.54
     LATEST
    -0.54
    POSITIVE LOGITS
     cherchés
    0.55
    ksikon
    0.52
     snippetHide
    0.51
     some
    0.50
    saraba
    0.50
    ويد
    0.48
    WebVitals
    0.48
     يتيمه
    0.47
    complexContent
    0.47
     CreateTagHelper
    0.46
    Activations Density 0.001%

    No Known Activations