© 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. 20-CLT-HP
    7. 77698
    Prev
    Next
    INDEX
    Explanations

    start different categories

    np_max-act-logits · 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
     somewhat
    -0.73
     Slightly
    -0.73
    somewhat
    -0.71
     slightly
    -0.70
     Somewhat
    -0.69
    slightly
    -0.64
     imperfect
    -0.64
     leſs
    -0.64
     less
    -0.63
    Somewhat
    -0.62
    POSITIVE LOGITS
     app
    0.63
     wo
    0.60
     outrage
    0.59
     '\\;'
    0.58
     grotes
    0.56
     مرئيه
    0.55
     EXT
    0.54
     negó
    0.53
     totalt
    0.53
    ArrowToggle
    0.53
    Activations Density 0.000%

    No Known Activations