© 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. 93036
    Prev
    Next
    INDEX
    Explanations

    article titles/descriptions

    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
    :
    -0.84
     two
    -0.74
     three
    -0.73
    ;
    -0.64
     four
    -0.64
     Wikimédia
    -0.63
     Two
    -0.61
     range
    -0.60
     Three
    -0.60
    IBAction
    -0.60
    POSITIVE LOGITS
     itſelf
    0.72
     ainfi
    0.71
     Paglinawan
    0.69
     Houſe
    0.68
     prossima
    0.68
     feroit
    0.67
     hiér
    0.67
     devenus
    0.65
     zelve
    0.64
     leaſt
    0.63
    Activations Density 0.001%

    No Known Activations