© 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. 0-CLT-HP
    7. 42660
    Prev
    Next
    INDEX
    Explanations

    Technical and downward trends

    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
    NewUrlParser
    -0.80
     typelib
    -0.73
     myſelf
    -0.68
     itſelf
    -0.67
     Numerade
    -0.66
     дописавши
    -0.65
    monium
    -0.65
     Berks
    -0.65
    vum
    -0.63
    )),
    -0.63
    POSITIVE LOGITS
    ly
    0.62
     kiện
    0.50
     []:
    0.48
     rechange
    0.45
    isé
    0.45
    strijd
    0.44
    LY
    0.43
    EUROPA
    0.43
     async
    0.42
    maßen
    0.41
    Activations Density 0.038%

    No Known Activations