© 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. 72380
    Prev
    Next
    INDEX
    Explanations

    activates

    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
    Kjelder
    -0.53
     nahilalakip
    -0.53
    CrossRef
    -0.51
    expandindo
    -0.50
    UpInside
    -0.47
    DockStyle
    -0.44
    LabelTagHelper
    -0.43
    la
    -0.43
     Sky
    -0.43
    La
    -0.43
    POSITIVE LOGITS
     houſe
    0.63
     Wikimedijinoj
    0.59
     Мексичка
    0.57
     specchio
    0.57
     betweenstory
    0.55
     Edd
    0.54
     fubject
    0.54
     ſtate
    0.54
     Gabby
    0.54
     purpoſe
    0.54
    Activations Density 0.001%

    No Known Activations