© 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. 91574
    Prev
    Next
    INDEX
    Explanations

    chance/unexpected events

    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
     wikipagina
    -0.58
    complexType
    -0.55
    Wouldn
    -0.54
    rägen
    -0.53
    Ārējās
    -0.53
     funny
    -0.52
     ComVisible
    -0.50
    twimg
    -0.50
    Huh
    -0.49
    accoon
    -0.49
    POSITIVE LOGITS
    sidemargin
    0.51
    Slf
    0.50
    DoubleQuotes
    0.48
    helves
    0.47
     createState
    0.46
     Cavalier
    0.45
    úly
    0.44
    ClientSize
    0.44
    alaya
    0.43
    avras
    0.43
    Activations Density 0.002%

    No Known Activations