© 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. 5-CLT-HP
    7. 4757
    Prev
    Next
    INDEX
    Explanations

    work

    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
    раздо
    -0.51
     onCreateView
    -0.50
     Clegg
    -0.46
    :✨
    -0.45
    HtmlAttribute
    -0.44
    xase
    -0.43
     समीक्षक
    -0.43
     gynnwys
    -0.42
    .");
    -0.41
    fromCharCode
    -0.41
    POSITIVE LOGITS
    awtextra
    0.68
    queryInterface
    0.63
    protoimpl
    0.63
    Rüyada
    0.60
    สือ
    0.59
     Sira
    0.54
     together
    0.52
     thus
    0.52
    ResumeLayout
    0.52
    atomy
    0.52
    Activations Density 0.002%

    No Known Activations