© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41735
    Prev
    Next
    INDEX
    Explanations

    electricity

    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
    AddTagHelper
    -1.09
    Personendaten
    -1.09
     للمعارف
    -1.01
     صوتيه
    -0.96
    ValueStyle
    -0.96
     تضيفلها
    -0.96
    InputBorder
    -0.96
     snippetHide
    -0.91
     resourceCulture
    -0.91
    RenderAtEndOf
    -0.91
    POSITIVE LOGITS
    ↵↵
    0.48
     matrices
    0.48
     gri
    0.48
     containing
    0.47
     of
    0.45
    </em>
    0.44
     material
    0.42
     end
    0.41
     placed
    0.41
     rather
    0.41
    Activations Density 0.040%

    No Known Activations