© 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. 95511
    Prev
    Next
    INDEX
    Explanations

    Pittsburgh and Seattle

    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
    monary
    -0.60
     esternos
    -0.56
     lenker
    -0.54
    ṇ
    -0.54
    fromnode
    -0.53
    rypt
    -0.53
     mergeFrom
    -0.53
     Nutz
    -0.47
    weich
    -0.46
    ellent
    -0.46
    POSITIVE LOGITS
    Vidite
    0.65
    oka
    0.60
    leetcode
    0.59
    hô
    0.59
    SCRIBE
    0.57
     Italijani
    0.56
    OKA
    0.56
    Biblia
    0.55
     Poche
    0.52
    andReturn
    0.52
    Activations Density 1.572%

    No Known Activations