© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10727
    Prev
    Next
    INDEX
    Explanations

    ron

    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
    astify
    -0.77
    yfik
    -0.70
    PageModule
    -0.66
     useAuth
    -0.65
     MutableLiveData
    -0.64
    migrationBuilder
    -0.63
    RegistryLite
    -0.61
     stimmt
    -0.60
    Distribuzione
    -0.60
    EDEFAULT
    -0.60
    POSITIVE LOGITS
    In
    0.43
    phosa
    0.43
     In
    0.43
     Following
    0.42
    Following
    0.42
    lainen
    0.41
     طريق
    0.40
    stackrel
    0.40
     électro
    0.40
     súb
    0.40
    Activations Density 0.599%

    No Known Activations