© 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. 20-CLT-HP
    7. 76498
    Prev
    Next
    INDEX
    Explanations

    development

    np_max-act-logits · 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
    sidemargin
    -0.60
     Roskov
    -0.54
    
    -0.51
    FXMLLoader
    -0.50
     xoay
    -0.49
     Wiseman
    -0.48
     Ricard
    -0.47
    etone
    -0.47
    bodyParser
    -0.47
    DataContract
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.73
    AnchorStyles
    0.58
    Оп
    0.54
    writeFieldEnd
    0.53
    ValueStyle
    0.52
    addCriterion
    0.50
    skraft
    0.48
    WithMany
    0.48
     Hendrix
    0.47
     createSprite
    0.47
    Activations Density 0.000%

    No Known Activations