© 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. 20-CLT-HP
    7. 75181
    Prev
    Next
    INDEX
    Explanations

    document excerpts

    np_max-act-logits · 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
    het
    -0.48
     Device
    -0.48
    et
    -0.46
     Studio
    -0.45
    ary
    -0.45
    dataTables
    -0.45
    hip
    -0.45
    cher
    -0.44
    ist
    -0.43
    ات
    -0.42
    POSITIVE LOGITS
    InitVars
    0.72
    mates
    0.72
    mice
    0.70
     autorytatywna
    0.68
     дописавши
    0.67
     NSCoder
    0.66
    cleaning
    0.66
    warming
    0.65
    awtextra
    0.64
    ніципалі
    0.63
    Activations Density 0.004%

    No Known Activations