© 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. 94359
    Prev
    Next
    INDEX
    Explanations

    delimiters/punctuation

    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
    MemoryWarning
    -0.93
     CURIAM
    -0.85
    RenderAtEndOf
    -0.74
    NUMX
    -0.73
     contextLoads
    -0.71
     мәкал
    -0.69
     viewDidLoad
    -0.68
    LLocation
    -0.67
    OGND
    -0.64
    ^(@)
    -0.64
    POSITIVE LOGITS
     a
    1.05
    a
    0.69
     ten
    0.52
     
    0.50
    stop
    0.50
    Continue
    0.47
    εσ
    0.46
    Stop
    0.46
    yani
    0.44
     действи
    0.43
    Activations Density 0.002%

    No Known Activations