© 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. 4-CLT-HP
    7. 4805
    Prev
    Next
    INDEX
    Explanations

    ela

    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
    Autoritní
    -0.66
    gartner
    -0.65
     CURLOPT
    -0.63
     TextInputType
    -0.60
    migrationBuilder
    -0.60
     DriverManager
    -0.58
     defaultstate
    -0.57
    CURLOPT
    -0.57
    principalColumn
    -0.57
    iastes
    -0.56
    POSITIVE LOGITS
     Harris
    0.62
    Harris
    0.54
     Har
    0.49
     Das
    0.48
     Hage
    0.48
    Das
    0.47
    Har
    0.46
     Hasan
    0.46
    Hasan
    0.45
    Ha
    0.44
    Activations Density 0.001%

    No Known Activations