© 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. 1-CLT-HP
    7. 13951
    Prev
    Next
    INDEX
    Explanations

    with

    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
     resourceCulture
    -0.73
     AssemblyCulture
    -0.63
     senaste
    -0.59
     InputDecoration
    -0.54
     proved
    -0.52
    المناصب
    -0.49
     svå
    -0.47
     længere
    -0.47
     lasted
    -0.46
     recent
    -0.46
    POSITIVE LOGITS
     tomorrow
    0.65
     Infórmanos
    0.63
     to
    0.61
    prepareStatement
    0.60
    iesti
    0.55
     morrow
    0.54
    '],$
    0.54
     henceforth
    0.54
     Gonna
    0.52
     Amis
    0.52
    Activations Density 0.022%

    No Known Activations