© 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. 1-CLT-HP
    7. 16080
    Prev
    Next
    INDEX
    Explanations

    2

    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
    
    -0.96
     للاسماء
    -0.94
     utafitiHapana
    -0.82
     consultato
    -0.76
     kasarigan
    -0.72
     udaler
    -0.69
     OFDb
    -0.68
    antMatchers
    -0.67
     елның
    -0.67
     AssemblyProduct
    -0.65
    POSITIVE LOGITS
     fully
    0.48
    .
    0.48
     view
    0.46
     look
    0.46
    regler
    0.42
    }")]
    0.42
     neck
    0.41
     state
    0.40
     complete
    0.40
    zard
    0.40
    Activations Density 0.033%

    No Known Activations