© 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. 1-CLT-HP
    7. 9429
    Prev
    Next
    INDEX
    Explanations

    institute

    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
     Institute
    -0.99
     INSTITUTE
    -0.90
    Institute
    -0.85
     institute
    -0.78
    tvguidetime
    -0.64
    institute
    -0.63
     يتيمه
    -0.59
     Institutes
    -0.58
    findpost
    -0.54
    хьтан
    -0.53
    POSITIVE LOGITS
    tagext
    0.59
     endwhile
    0.54
     kaynağından
    0.54
     (£
    0.50
    writerow
    0.50
    vinas
    0.49
    antMatchers
    0.49
     Paxton
    0.48
    webElementXpaths
    0.48
    msc
    0.48
    Activations Density 0.045%

    No Known Activations