© 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. 5-CLT-HP
    7. 6193
    Prev
    Next
    INDEX
    Explanations

    c

    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
     Polak
    -0.50
    tempel
    -0.49
     என்ற
    -0.45
    osoever
    -0.45
     Mey
    -0.44
    msgSender
    -0.44
    elstein
    -0.44
    bieter
    -0.43
     clés
    -0.43
     COUNTER
    -0.43
    POSITIVE LOGITS
    kháu
    0.62
    IntoConstraints
    0.60
    IndentedString
    0.59
    mui
    0.57
     purpoſe
    0.56
     يتيمه
    0.54
     ſtate
    0.53
    AnchorStyles
    0.52
     AppCompatTheme
    0.52
    fjspx
    0.52
    Activations Density 0.000%

    No Known Activations