© 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. 40056
    Prev
    Next
    INDEX
    Explanations

    The

    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
     Pau
    -0.52
     A
    -0.47
     O
    -0.44
     _
    -0.42
     most
    -0.41
     E
    -0.40
    ものである
    -0.40
     He
    -0.39
     K
    -0.39
    ณะ
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    0.90
    tagHelperRunner
    0.88
    WriteTagHelper
    0.82
     EconPapers
    0.81
     invokingState
    0.80
     userSchema
    0.79
     photolibrary
    0.77
     auffi
    0.75
    SourceChecksum
    0.75
    Personensuche
    0.74
    Activations Density 0.317%

    No Known Activations