© 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. 8616
    Prev
    Next
    INDEX
    Explanations

    arms

    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
    itinéraire
    -0.46
     facilite
    -0.44
     TMS
    -0.44
     chaleco
    -0.44
     puisse
    -0.43
    ksesta
    -0.43
     Fuchs
    -0.43
     refusé
    -0.42
    esse
    -0.41
     Améli
    -0.40
    POSITIVE LOGITS
     архивлан
    0.77
    CodedInputStream
    0.73
    rungsseite
    0.65
    PyExc
    0.65
     Administrativna
    0.64
     nahilalakip
    0.60
     Walkover
    0.60
     Canopy
    0.59
     unknownFields
    0.59
    ыгана
    0.57
    Activations Density 0.134%

    No Known Activations