© 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. 0-CLT-HP
    7. 93679
    Prev
    Next
    INDEX
    Explanations

    aylor

    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
    aylor
    -0.73
     syn
    -0.65
    Syn
    -0.58
    syn
    -0.57
     Gegenteil
    -0.57
     Efq
    -0.57
     NSCoder
    -0.57
    hia
    -0.56
     Syn
    -0.56
     canadensis
    -0.56
    POSITIVE LOGITS
    ViewFeatures
    0.61
     EClass
    0.59
     betweenstory
    0.57
     pères
    0.56
    serum
    0.54
    podium
    0.50
    neurial
    0.48
    andum
    0.47
    bibliothek
    0.47
     telefónica
    0.46
    Activations Density 0.064%

    No Known Activations