© 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. 0-CLT-HP
    7. 92714
    Prev
    Next
    INDEX
    Explanations

    related

    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
     Савезне
    -0.83
    ThroughAttribute
    -0.79
    بوابة
    -0.77
    Datuak
    -0.77
    verwijspagina
    -0.74
     aikaa
    -0.74
    endphp
    -0.73
    AntiForgeryToken
    -0.73
     gyhoeddwyd
    -0.72
     pitié
    -0.72
    POSITIVE LOGITS
     capo
    0.46
    Κ
    0.44
     kim
    0.43
     tồn
    0.42
     bene
    0.42
    "/>
    0.42
    figsize
    0.40
    intent
    0.40
     spod
    0.39
     chance
    0.39
    Activations Density 0.167%

    No Known Activations