© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 438
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.60
     eels
    -0.58
     fingernails
    -0.56
     BigNumber
    -0.55
     Lauder
    -0.54
     necklaces
    -0.52
     alumina
    -0.52
     pigs
    -0.52
     daf
    -0.52
     snails
    -0.50
    POSITIVE LOGITS
    <bos>
    0.88
     الرياضيه
    0.53
    ControllerTest
    0.51
    Sklici
    0.50
    HandlerContext
    0.50
    getMenuInflater
    0.46
     सत्यापित
    0.46
     for
    0.45
    ukone
    0.44
    RTGC
    0.44
    Activations Density 0.030%

    No Known Activations