© 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. 71281
    Prev
    Next
    INDEX
    Explanations

    as

    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
    principalColumn
    -0.85
    AndEndTag
    -0.71
    //
    -0.65
    Портал
    -0.62
    ::_('
    -0.61
    SpringBootTest
    -0.60
    исленность
    -0.60
    EndGlobalSection
    -0.59
    alous
    -0.58
    clusão
    -0.58
    POSITIVE LOGITS
     as
    1.24
    as
    0.65
     sebagai
    0.63
     As
    0.62
     как
    0.56
    As
    0.52
     качестве
    0.51
     bilang
    0.51
     enquanto
    0.51
    作为
    0.50
    Activations Density 0.053%

    No Known Activations