© 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. 0-CLT-HP
    7. 94334
    Prev
    Next
    INDEX
    Explanations

    tial

    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
    tias
    -1.00
    tial
    -0.88
    ArrowToggle
    -0.79
     pinulongan
    -0.74
    Démographie
    -0.74
    GraphicsUnit
    -0.69
     creatively
    -0.69
     linkovi
    -0.69
     otomatig
    -0.66
     bezeichneter
    -0.66
    POSITIVE LOGITS
    o
    0.53
     fratello
    0.52
    es
    0.48
    
    0.48
    b
    0.47
     Container
    0.44
     inspiração
    0.44
    e
    0.44
     Herald
    0.43
    hbar
    0.43
    Activations Density 0.027%

    No Known Activations