© 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. 45586
    Prev
    Next
    INDEX
    Explanations

    irradiation

    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
    ly
    -0.86
     الحره
    -0.86
    neté
    -0.85
     mediocrity
    -0.82
     Exactos
    -0.80
     negotiator
    -0.79
    istoitu
    -0.78
     محفوظة
    -0.77
    ed
    -0.76
     חיצוניים
    -0.76
    POSITIVE LOGITS
    はじめに
    0.46
     company
    0.40
     forma
    0.38
     Ngb
    0.38
     mode
    0.37
     reduction
    0.37
     eins
    0.37
     som
    0.36
     instead
    0.36
     Historic
    0.36
    Activations Density 0.368%

    No Known Activations