© 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. 9934
    Prev
    Next
    INDEX
    Explanations

    ton

    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
    ViewImports
    -0.57
    ilever
    -0.54
    AutoScale
    -0.52
    :✨
    -0.52
    shub
    -0.51
    DIPSETTING
    -0.51
     '{@
    -0.49
    titleMargin
    -0.49
    Население
    -0.48
     sqlSession
    -0.47
    POSITIVE LOGITS
    
    0.61
     whoſe
    0.59
     فريبيس
    0.59
     Besoin
    0.56
     lode
    0.56
     ſhe
    0.55
     Arjuna
    0.54
     Anſ
    0.52
     везе
    0.52
     mandi
    0.52
    Activations Density 0.042%

    No Known Activations