© 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. 5413
    Prev
    Next
    INDEX
    Explanations

    Months and dates

    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
    :+:
    -0.59
     disponibilités
    -0.56
     Sylvain
    -0.55
     praktijk
    -0.54
     auffi
    -0.54
    selaer
    -0.54
    ITIES
    -0.54
     quæ
    -0.54
    CloseOperation
    -0.53
     itſelf
    -0.53
    POSITIVE LOGITS
    ArgumentParser
    0.52
    XmlAccessType
    0.50
    umar
    0.45
     cielos
    0.44
     linkovi
    0.42
    gon
    0.42
    geocode
    0.41
    coroutines
    0.41
    sidemargin
    0.40
    Anhalt
    0.40
    Activations Density 0.001%

    No Known Activations