© 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. 4-CLT-HP
    7. 1839
    Prev
    Next
    INDEX
    Explanations

    this

    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
    StoryboardSegue
    -0.87
    niająca
    -0.72
    Билгалдахарш
    -0.69
     AssemblyCompany
    -0.64
     lenker
    -0.64
    VersionUID
    -0.63
     Савезне
    -0.62
     विश्वसनीयता
    -0.62
     BorderRadius
    -0.61
     ModelExpression
    -0.61
    POSITIVE LOGITS
     contained
    0.59
     involved
    0.54
     added
    0.53
     concerned
    0.52
     explored
    0.52
     individual
    0.52
     revealed
    0.50
     queried
    0.50
    involved
    0.50
     dealt
    0.49
    Activations Density 0.001%

    No Known Activations