© 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. 96780
    Prev
    Next
    INDEX
    Explanations

    causes/factors of problems

    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
    ništ
    -0.55
     kohdetta
    -0.55
     lenker
    -0.52
    ịp
    -0.51
     åt
    -0.49
    howto
    -0.46
     serangga
    -0.46
    AutoresizingMask
    -0.46
     jadx
    -0.46
    intios
    -0.45
    POSITIVE LOGITS
     remains
    0.73
     appears
    0.73
     comes
    0.73
     relies
    0.71
     was
    0.71
     seems
    0.70
     depends
    0.70
     derives
    0.69
     varies
    0.68
     isn
    0.66
    Activations Density 0.002%

    No Known Activations