© 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. 71377
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    Negative Logits
    LEncoder
    -0.68
    ]--;
    -0.65
    lcc
    -0.54
    Slf
    -0.52
    lan
    -0.51
    BagConstraints
    -0.50
    lin
    -0.50
    liz
    -0.49
    ]-->
    -0.49
     tables
    -0.48
    POSITIVE LOGITS
    ьаж
    0.58
     useAppContext
    0.49
    __((
    0.45
    astify
    0.43
    Seventh
    0.43
     Arkham
    0.43
     PHA
    0.43
    parsedMessage
    0.43
     démocratie
    0.43
    ersatz
    0.43
    Activations Density 0.002%

    No Known Activations