© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78241
    Prev
    Next
    INDEX
    Explanations

    Code snippets/documentation

    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
    Negative Logits
     يتيمه
    -0.69
    SourceChecksum
    -0.68
    GOTREF
    -0.58
    RenderAtEndOf
    -0.57
    AndEndTag
    -0.56
    قایناقلار
    -0.56
     iprot
    -0.55
    vats
    -0.53
     Numer
    -0.51
     pinulongan
    -0.51
    POSITIVE LOGITS
    ine
    0.54
     Anti
    0.51
    INE
    0.50
     anti
    0.50
    Anti
    0.49
    anti
    0.47
    DeleteBehavior
    0.46
    ={`/
    0.46
    anas
    0.46
    jectures
    0.45
    Activations Density 0.004%

    No Known Activations