© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42756
    Prev
    Next
    INDEX
    Explanations

    Code, foreign characters, names

    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
     AssemblyTitle
    -0.82
    InstanceState
    -0.73
    ffilm
    -0.62
    MemoryWarning
    -0.61
    Datuak
    -0.56
    +#+
    -0.56
    personen
    -0.54
    aryen
    -0.54
    ้ม
    -0.53
    IntoConstraints
    -0.52
    POSITIVE LOGITS
     ''){
    0.61
     تعدى
    0.53
    دانشنامهٔ
    0.52
     samar
    0.51
     Belleville
    0.51
     GoogleFonts
    0.51
     recoveries
    0.50
     '').
    0.50
     җ
    0.50
     habitudes
    0.50
    Activations Density 1.834%

    No Known Activations