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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94901
    Prev
    Next
    INDEX
    Explanations

    Academic/Research texts

    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
     handker
    -0.57
     linseed
    -0.56
     ſhould
    -0.55
     whoſe
    -0.54
    TagMode
    -0.53
     eenige
    -0.52
     uſed
    -0.52
     ſhall
    -0.52
     كومونز
    -0.52
     ſta
    -0.52
    POSITIVE LOGITS
     Energy
    0.58
    zarchiwizowane
    0.56
     newBuilder
    0.56
     Origins
    0.55
    mockito
    0.54
     Status
    0.54
     <",
    0.54
    jsxFileName
    0.54
    AddTagHelper
    0.53
    Autoritní
    0.53
    Activations Density 0.002%

    No Known Activations