© 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. 4409
    Prev
    Next
    INDEX
    Explanations

    bad

    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
    jsonwebtoken
    -0.69
    تقاوى
    -0.67
    GEBURTSDATUM
    -0.64
     Paglinawan
    -0.63
    PerformLayout
    -0.61
    minecraftforge
    -0.61
    mergeFrom
    -0.60
     nahilalakip
    -0.60
    OGND
    -0.59
    примеча
    -0.58
    POSITIVE LOGITS
     case
    0.50
     sunburn
    0.49
     crash
    0.48
     mood
    0.48
    enough
    0.48
     wreck
    0.46
     break
    0.46
     storm
    0.46
     mistake
    0.46
     day
    0.45
    Activations Density 0.001%

    No Known Activations