© 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. 6162
    Prev
    Next
    INDEX
    Explanations

    food

    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
    قایناق‌لار
    -0.51
    Geografi
    -0.48
    IonicModule
    -0.45
    __":
    -0.43
    lapsingToolbar
    -0.43
     doInBackground
    -0.42
    +#+
    -0.42
     Assignee
    -0.42
    MenuInflater
    -0.41
    ueses
    -0.41
    POSITIVE LOGITS
    ValueGeneration
    0.59
     Schlüssel
    0.55
     Keys
    0.54
    pruch
    0.54
    躇
    0.54
     Ballon
    0.51
     Domes
    0.50
    apnews
    0.50
    ẩm
    0.50
    ณา
    0.50
    Activations Density 0.009%

    No Known Activations