© 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. 20-CLT-HP
    7. 72891
    Prev
    Next
    INDEX
    Explanations

    Random text

    np_max-act-logits · 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
    InteropServices
    -0.63
    initializeApp
    -0.57
    mergeFrom
    -0.56
    HasOne
    -0.56
    XmlRootElement
    -0.56
     Dickerson
    -0.55
    zzang
    -0.55
    ruled
    -0.54
    Населення
    -0.53
     Ethnicity
    -0.53
    POSITIVE LOGITS
    rungsseite
    0.62
    
    0.56
    SBATCH
    0.56
    الحياه
    0.54
     betweenstory
    0.48
    ActionCreators
    0.47
    setAccessible
    0.46
    AutoresizingMask
    0.44
    enumi
    0.43
    exitRule
    0.42
    Activations Density 0.000%

    No Known Activations