© 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. 5-CLT-HP
    7. 92127
    Prev
    Next
    INDEX
    Explanations

    bottom

    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
    Jeografia
    -0.68
    ########.
    -0.60
    rawDesc
    -0.59
    webElementXpaths
    -0.57
     intptr
    -0.54
    AsUp
    -0.54
     lourdes
    -0.53
     málaga
    -0.53
    SpringBootTest
    -0.52
     @"/
    -0.52
    POSITIVE LOGITS
     line
    0.87
     Line
    0.68
     lines
    0.65
     Lines
    0.59
    Line
    0.53
    AxisAlignment
    0.53
     lijn
    0.52
     LINE
    0.52
    line
    0.48
    addPreferredGap
    0.47
    Activations Density 0.003%

    No Known Activations