© 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. 0-CLT-HP
    7. 95514
    Prev
    Next
    INDEX
    Explanations

    holds

    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
    Negative Logits
     dropped
    -0.81
     stands
    -0.74
     holds
    -0.72
     speaks
    -0.68
    sterious
    -0.66
    dropped
    -0.62
     spoke
    -0.60
     drops
    -0.59
     Perhaps
    -0.56
     poses
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.63
     Anſ
    0.62
    RunAsync
    0.60
    Newswire
    0.57
     réal
    0.56
     vapour
    0.55
     AssemblyCompany
    0.55
    ไตล
    0.55
    AnchorStyles
    0.54
    AdapterFactory
    0.54
    Activations Density 0.261%

    No Known Activations