© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 819
    Prev
    Next
    INDEX
    Explanations

    prefixes mis over

    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
     scaling
    -0.73
     mixing
    -0.71
     marking
    -0.68
     setting
    -0.66
     rooting
    -0.66
     settings
    -0.65
     rendering
    -0.65
     plotting
    -0.65
     streaming
    -0.64
     casting
    -0.64
    POSITIVE LOGITS
    AndEndTag
    0.81
    AddTagHelper
    0.81
    InjectAttribute
    0.73
     يتيمه
    0.71
    PerformLayout
    0.69
     survie
    0.66
     invokingState
    0.64
    saraba
    0.64
    Derbyniad
    0.62
     externi
    0.60
    Activations Density 0.002%

    No Known Activations