© 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. 93769
    Prev
    Next
    INDEX
    Explanations

    =

    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
     Majefty
    -0.69
     purpoſe
    -0.68
     pleaſure
    -0.67
     raiſ
    -0.67
     houſe
    -0.65
     isComment
    -0.64
     myſelf
    -0.64
     ་་
    -0.59
     ſta
    -0.57
    $")
    -0.56
    POSITIVE LOGITS
     épaules
    0.64
     متعلقه
    0.60
     hâte
    0.56
     NSCoder
    0.54
    NCR
    0.54
     inteligentes
    0.54
    capabilities
    0.54
    ̶
    0.54
     finestra
    0.53
    väg
    0.53
    Activations Density 0.003%

    No Known Activations