© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92934
    Prev
    Next
    INDEX
    Explanations

    software/coding

    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
    
    -0.63
     utafitiHapana
    -0.57
    >();
    -0.56
     跳转至
    -0.52
     Rudd
    -0.52
    rénées
    -0.52
    Jährige
    -0.52
     largest
    -0.52
     jScrollPane
    -0.51
    rungsseite
    -0.51
    POSITIVE LOGITS
     aveug
    0.59
    argout
    0.57
    HashCode
    0.54
     térmica
    0.52
    complexContent
    0.52
     Wikimedijinoj
    0.51
     CreateTagHelper
    0.50
     distanza
    0.50
     répon
    0.50
     réforme
    0.50
    Activations Density 0.001%

    No Known Activations