© 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. 1-CLT-HP
    7. 14898
    Prev
    Next
    INDEX
    Explanations

    Cumberland

    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
     المعيارى
    -0.90
    
    -0.60
     Waterways
    -0.54
    ThroughAttribute
    -0.54
    évaluateur
    -0.52
     Cumberland
    -0.52
    ArrowToggle
    -0.50
     turnout
    -0.49
     Cinderella
    -0.48
    inderella
    -0.47
    POSITIVE LOGITS
    edly
    0.56
    e
    0.56
    ISupport
    0.56
    ableness
    0.55
    ed
    0.55
    اظ
    0.54
    aine
    0.52
    es
    0.49
    jährigen
    0.49
    ados
    0.49
    Activations Density 0.009%

    No Known Activations