© 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. 0-CLT-HP
    7. 94631
    Prev
    Next
    INDEX
    Explanations

    Niche topics

    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
    ker
    -0.57
    قلال
    -0.56
    Gweler
    -0.53
    analyser
    -0.52
     Cæsar
    -0.52
    Спасибо
    -0.50
    erste
    -0.49
    Analyte
    -0.49
    woł
    -0.49
    },[])
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.63
     незавершена
    0.59
    uxxxx
    0.58
    atshirt
    0.56
    DispatchToProps
    0.55
    Personensuche
    0.52
     LoggerFactory
    0.52
     Baillargeon
    0.52
    i
    0.52
     AssemblyProduct
    0.52
    Activations Density 1.023%

    No Known Activations