© 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. 5-CLT-HP
    7. 91234
    Prev
    Next
    INDEX
    Explanations

    Returning / Reversing

    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
     again
    -0.66
     Again
    -0.61
    Again
    -0.60
     CreateTagHelper
    -0.54
    ValueStyle
    -0.52
     Gegenteil
    -0.50
     renewed
    -0.50
     مشين
    -0.49
    again
    -0.49
    ")));
    -0.49
    POSITIVE LOGITS
    WebpackPlugin
    0.63
    الدراسه
    0.62
     nakalista
    0.57
     EconPapers
    0.54
    談社
    0.53
     élector
    0.53
     cytok
    0.52
    ouan
    0.52
    EndGlobalSection
    0.52
     colpo
    0.52
    Activations Density 0.002%

    No Known Activations