© 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. 5-CLT-HP
    7. 84
    Prev
    Next
    INDEX
    Explanations

    here

    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
    CppMethod
    -0.78
     فريبيس
    -0.66
    ]")]
    -0.65
    ChildScrollView
    -0.65
     insuffisamment
    -0.62
    aarrggbb
    -0.62
     تضيفلها
    -0.61
     nakalista
    -0.60
     становника
    -0.60
    WithIOException
    -0.58
    POSITIVE LOGITS
    ulemon
    0.42
    országban
    0.42
     ainda
    0.41
     Teraz
    0.41
     now
    0.40
     fiind
    0.40
    Sucesor
    0.40
     autorytatywna
    0.39
     would
    0.39
     They
    0.39
    Activations Density 0.005%

    No Known Activations