© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97499
    Prev
    Next
    INDEX
    Explanations

    code or formal language

    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
     []),
    -0.50
     "",
    -0.50
     '',
    -0.50
     tendances
    -0.49
     turning
    -0.49
     pouss
    -0.48
     Diſ
    -0.48
     turns
    -0.48
     Turn
    -0.48
     ſta
    -0.48
    POSITIVE LOGITS
    routeProvider
    0.83
    CloseOperation
    0.69
     lenker
    0.67
    MockMvc
    0.66
    Solución
    0.63
    ]='\
    0.61
    fromCharCode
    0.60
    CodeDom
    0.60
    cookieParser
    0.59
    makeText
    0.58
    Activations Density 0.003%

    No Known Activations