© 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. 5532
    Prev
    Next
    INDEX
    Explanations

    dense

    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
    tvguidetime
    -0.95
     متعلقه
    -0.68
    PerformLayout
    -0.68
     محفوظة
    -0.66
    extAlignment
    -0.64
     EconPapers
    -0.64
     initComponents
    -0.63
    Atsauces
    -0.63
    KommentareTeilen
    -0.62
    ValueStyle
    -0.62
    POSITIVE LOGITS
     under
    0.45
     ma
    0.45
     for
    0.44
     can
    0.43
    CDATA
    0.43
     Australian
    0.43
     For
    0.41
     Under
    0.41
     Alaskan
    0.41
     kita
    0.41
    Activations Density 0.002%

    No Known Activations