© 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. 5-CLT-HP
    7. 2683
    Prev
    Next
    INDEX
    Explanations

    Dodd name

    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
    Portale
    -0.64
    ChildScrollView
    -0.63
    }{*}{}
    -0.55
    ềm
    -0.53
    calientes
    -0.52
     صوتيه
    -0.51
    ünst
    -0.50
    PointerException
    -0.48
     NDL
    -0.48
     virtu
    -0.48
    POSITIVE LOGITS
    Frank
    0.64
     Frank
    0.60
     Franke
    0.59
    EndContext
    0.57
    contentLoaded
    0.54
    Fran
    0.51
    AccessorTable
    0.51
    Xaml
    0.50
    FRANK
    0.50
     Franks
    0.49
    Activations Density 0.005%

    No Known Activations