© 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. 92461
    Prev
    Next
    INDEX
    Explanations

    Application of resources/methods

    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
    expandindo
    -1.47
    EndContext
    -1.22
    GEBURTSDATUM
    -1.18
    SourceChecksum
    -1.16
     otomatig
    -1.12
    providedIn
    -1.10
    InjectAttribute
    -1.09
    webElementXpaths
    -1.09
     المعيارى
    -1.09
    DockStyle
    -1.08
    POSITIVE LOGITS
     by
    0.84
     in
    0.52
     to
    0.50
     so
    0.47
     use
    0.43
     hard
    0.42
     way
    0.41
     lett
    0.39
     non
    0.39
     im
    0.38
    Activations Density 0.038%

    No Known Activations