© 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. 4-CLT-HP
    7. 4994
    Prev
    Next
    INDEX
    Explanations

    images

    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
    GenerationType
    -0.59
    tvguidetime
    -0.55
    ToMany
    -0.54
    脚注の使い方
    -0.53
    openapi
    -0.53
    ']))
    -0.52
     Sound
    -0.50
    theoremstyle
    -0.50
    Sound
    -0.50
    ætte
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.68
    abetes
    0.60
     dAtA
    0.59
     depic
    0.59
     تضيفلها
    0.57
    RenderAtEndOf
    0.55
     show
    0.54
     depict
    0.52
     mariée
    0.52
     depicts
    0.52
    Activations Density 0.003%

    No Known Activations