© 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. 2482
    Prev
    Next
    INDEX
    Explanations

    prefer

    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
     fieldNum
    -0.80
    BeginContext
    -0.80
    addGap
    -0.75
    Демографія
    -0.73
    Datuak
    -0.72
    ographers
    -0.71
    MemoryWarning
    -0.69
    Gön
    -0.69
    atguigu
    -0.68
    HostException
    -0.68
    POSITIVE LOGITS
     not
    0.55
    not
    0.49
    CDCl
    0.43
    pot
    0.42
     portato
    0.41
     tidak
    0.41
     não
    0.40
     farlo
    0.40
     niega
    0.39
     faceva
    0.37
    Activations Density 0.030%

    No Known Activations