© 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. 4081
    Prev
    Next
    INDEX
    Explanations

    Hawaii

    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
    }{*}{
    -0.59
    cada
    -0.52
     jScrollPane
    -0.51
     Comunic
    -0.51
    Personendaten
    -0.50
     playa
    -0.49
     Wiktionnaire
    -0.48
    illan
    -0.48
    arate
    -0.47
     Cantor
    -0.47
    POSITIVE LOGITS
     transfieras
    0.58
    sidemargin
    0.57
     AssemblyCulture
    0.55
     Emits
    0.55
     NSCoder
    0.53
    AutoScaleMode
    0.53
    nextProps
    0.50
     AssemblyCompany
    0.50
    asteroide
    0.50
    voie
    0.49
    Activations Density 0.002%

    No Known Activations