© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2761
    Prev
    Next
    INDEX
    Explanations

    gabriel

    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
     (~
    -0.40
    ↵↵
    -0.40
    issaient
    -0.38
     Started
    -0.38
    héro
    -0.37
     bille
    -0.34
     пришлось
    -0.34
    issait
    -0.34
    Realistic
    -0.33
    тельный
    -0.33
    POSITIVE LOGITS
     surla
    0.85
    zzleHttp
    0.85
    PerformLayout
    0.85
    Autoritní
    0.85
    دانشنامهٔ
    0.84
    Välislingid
    0.83
    GEBURTSDATUM
    0.83
     חיצוניים
    0.83
     AssemblyVersion
    0.82
     disambiguazione
    0.80
    Activations Density 0.000%

    No Known Activations