© 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. 41708
    Prev
    Next
    INDEX
    Explanations

    ****************

    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
     Prow
    -0.60
    poptosis
    -0.57
     Auctions
    -0.57
    Cyfeiriadau
    -0.53
     Sodom
    -0.52
     propOrder
    -0.52
    րջ
    -0.51
     Whence
    -0.51
     Rata
    -0.51
     starlight
    -0.51
    POSITIVE LOGITS
    Portály
    0.74
    sidemargin
    0.71
    httphttps
    0.68
     незавершена
    0.67
    MathML
    0.64
    ')}}
    0.60
     saites
    0.55
     nahilalakip
    0.54
     deines
    0.54
    $}}
    0.53
    Activations Density 0.156%

    No Known Activations