© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74457
    Prev
    Next
    INDEX
    Explanations

    Code and data labels

    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
    aarrggbb
    -0.76
     propOrder
    -0.73
    WriteBarrier
    -0.64
    XmlAccessorType
    -0.61
    GeoNames
    -0.61
    hyrchwyd
    -0.58
     '\\;'
    -0.57
     continúas
    -0.53
     noDo
    -0.52
     Fiske
    -0.52
    POSITIVE LOGITS
    isNameExpr
    0.52
    !*\
    0.48
    ']))
    
    0.46
    abestanden
    0.46
    SuppressMessage
    0.45
    ResumeLayout
    0.45
    tagHelperRunner
    0.45
     Pré
    0.45
     payé
    0.43
    "]];
    0.42
    Activations Density 0.000%

    No Known Activations