© 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. 4622
    Prev
    Next
    INDEX
    Explanations

    previous

    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
    MessageTagHelper
    -0.86
    tvguidetime
    -0.62
    Kanpo
    -0.60
     חיצוניים
    -0.58
    Identyfik
    -0.57
     végétale
    -0.57
     nahilalakip
    -0.56
     sogget
    -0.56
    RTSC
    -0.55
     logique
    -0.55
    POSITIVE LOGITS
    kháu
    0.51
     forever
    0.50
    uanya
    0.49
     FOREVER
    0.44
     tongues
    0.44
    ⓧ
    0.43
     someday
    0.43
    führen
    0.42
     stew
    0.42
     indefinitely
    0.42
    Activations Density 0.005%

    No Known Activations