© 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. 5-CLT-HP
    7. 92227
    Prev
    Next
    INDEX
    Explanations

    Some

    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
    ğine
    -0.52
    heartedly
    -0.50
     aleación
    -0.49
    事
    -0.48
    vées
    -0.48
     
    -0.48
    IZAR
    -0.47
    legungen
    -0.47
     naselje
    -0.47
    itung
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.67
    principalTable
    0.65
     مشين
    0.62
     AssemblyTitle
    0.60
    ."</
    0.58
    tagHelperRunner
    0.57
     of
    0.57
    PreferredItem
    0.56
    MLLoader
    0.56
     TextAppearance
    0.55
    Activations Density 0.001%

    No Known Activations