© 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. 5270
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    hyrchwyd
    -0.71
     autorytatywna
    -0.64
    webElementXpaths
    -0.63
     øns
    -0.61
    InjectAttribute
    -0.61
    Kann
    -0.60
     navideñas
    -0.59
     artísticas
    -0.59
     tartalomajánló
    -0.57
     kasarigan
    -0.56
    POSITIVE LOGITS
    findpost
    0.59
    ollectionView
    0.56
     المتحدة
    0.54
     cellpadding
    0.49
    igshid
    0.46
     setEmail
    0.45
     areal
    0.45
    readystatechange
    0.44
     bids
    0.44
     Seaman
    0.44
    Activations Density 0.007%

    No Known Activations