© 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. 77968
    Prev
    Next
    INDEX
    Explanations

    code and unique sentences

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.54
     ſever
    -0.51
    ########.
    -0.51
     Мексичка
    -0.49
     doubtnut
    -0.48
     purpoſe
    -0.48
     Monfieur
    -0.47
    ismet
    -0.47
     ſtate
    -0.45
     Pyrene
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.61
    featureID
    0.60
     VIAF
    0.60
    principalColumn
    0.59
     TextInputType
    0.57
     Corn
    0.56
     Familienname
    0.55
     Flying
    0.54
     inflater
    0.54
    forChild
    0.53
    Activations Density 0.000%

    No Known Activations