© 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. 90855
    Prev
    Next
    INDEX
    Explanations

    and

    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
    transQ
    -0.76
    chables
    -0.74
     Yaz
    -0.73
    Portail
    -0.72
    válasz
    -0.72
    .”.
    -0.71
    rawDesc
    -0.71
     HDR
    -0.71
     invo
    -0.70
    parsedMessage
    -0.70
    POSITIVE LOGITS
     صوتيه
    0.43
    Източници
    0.42
    Lähteet
    0.41
    ۜ
    0.34
     convertView
    0.33
    tagHelperRunner
    0.32
     poveznice
    0.31
     vänner
    0.31
    UnusedPrivate
    0.30
     HttpNotFound
    0.30
    Activations Density 0.005%

    No Known Activations