© 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. 95578
    Prev
    Next
    INDEX
    Explanations

    programming and computers

    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
     si
    -0.60
    ing
    -0.54
     li
    -0.50
     pi
    -0.50
    yl
    -0.49
     lay
    -0.48
     size
    -0.48
    e
    -0.47
     plan
    -0.46
    oine
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.99
     Efq
    0.95
     Monfieur
    0.88
     Majefty
    0.84
     Reſ
    0.79
    __':
    0.76
    TagMode
    0.75
     Houſe
    0.75
     Jefus
    0.74
     myſelf
    0.74
    Activations Density 0.084%

    No Known Activations