© 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. 71518
    Prev
    Next
    INDEX
    Explanations

    unusual technical language

    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
    ereco
    -0.56
     himo
    -0.55
    hematical
    -0.52
     VOW
    -0.50
    '):
    -0.49
    lint
    -0.47
    ]!='
    -0.46
     Himo
    -0.44
    liston
    -0.44
     Items
    -0.44
    POSITIVE LOGITS
    enumi
    0.75
    ReusableCell
    0.75
     Chwiliwch
    0.75
    ValueStyle
    0.63
     JpaRepository
    0.63
     consultato
    0.59
    Personensuche
    0.58
     [*]
    0.58
     defaultstate
    0.57
    
    0.57
    Activations Density 0.000%

    No Known Activations