© 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. 5-CLT-HP
    7. 3553
    Prev
    Next
    INDEX
    Explanations

    time

    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
     الحره
    -0.71
    .
    -0.55
    ,
    -0.54
    expandindo
    -0.51
     produisons
    -0.51
     hObject
    -0.49
    Билгалдахарш
    -0.49
    atzung
    -0.48
    EVAL
    -0.48
    TagHelpers
    -0.48
    POSITIVE LOGITS
    InitVars
    0.63
    PreferredItem
    0.60
     Paglinawan
    0.59
     snippetHide
    0.56
    uride
    0.55
    queryInterface
    0.54
    Portale
    0.53
    TagMode
    0.52
    <caption>
    0.50
     nakalista
    0.50
    Activations Density 0.003%

    No Known Activations