© 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. 2718
    Prev
    Next
    INDEX
    Explanations

    N/A

    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
    principalTable
    -0.57
     intptr
    -0.54
    enschappelijke
    -0.48
     strip
    -0.48
    حياته
    -0.46
    期刊论文
    -0.46
    ">—
    -0.45
    javadoc
    -0.45
     bug
    -0.45
     =",
    -0.44
    POSITIVE LOGITS
     aveug
    0.70
    MemoryWarning
    0.60
     extérieurs
    0.59
     découver
    0.58
     découvertes
    0.56
     extré
    0.55
     démocr
    0.55
     fermés
    0.55
     régl
    0.54
     végétal
    0.53
    Activations Density 0.007%

    No Known Activations