© 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. 5-CLT-HP
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    also/been

    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
    StructEnd
    -0.90
    LookAnd
    -0.82
    ंदीखरीदारी
    -0.80
     betweenstory
    -0.70
     ujednoznacz
    -0.70
    はじめに
    -0.68
    ContentAsync
    -0.68
    UnusedPrivate
    -0.66
    AndEndTag
    -0.62
    PerformLayout
    -0.61
    POSITIVE LOGITS
    HasForeignKey
    0.66
    nyk
    0.52
    ASSOC
    0.52
     показа
    0.50
    TestingModule
    0.49
     IBOutlet
    0.48
     identifiés
    0.48
     the
    0.46
    UrlResolution
    0.46
     menghub
    0.45
    Activations Density 0.003%

    No Known Activations