© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    perfect

    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
     case
    -0.49
     bulunabilir
    -0.48
    ts
    -0.46
    показания
    -0.45
    arie
    -0.45
    LLocation
    -0.44
     Wikimedijinoj
    -0.44
     cellular
    -0.44
    balleur
    -0.44
     longue
    -0.43
    POSITIVE LOGITS
     Signalez
    0.69
    reportWebVitals
    0.66
    تقاوى
    0.65
    новништво
    0.63
     nahilalakip
    0.59
     AssemblyVersion
    0.57
     الحره
    0.57
    ValueGenerated
    0.56
    GeneratedValue
    0.56
    RetentionPolicy
    0.56
    Activations Density 0.003%

    No Known Activations