© 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. 91481
    Prev
    Next
    INDEX
    Explanations

    informing, legal

    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
     ouverte
    -0.50
     fermée
    -0.48
     skydd
    -0.48
     extérieure
    -0.48
     löyty
    -0.47
     économiques
    -0.46
    ásban
    -0.45
    िप
    -0.45
     concorso
    -0.44
     élevées
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.82
    endphp
    0.76
    GEBURTS
    0.75
    TagMode
    0.71
     the
    0.71
     nakalista
    0.69
     виправивши
    0.68
     الرياضيه
    0.67
    tanleria
    0.66
    بوابة
    0.66
    Activations Density 0.001%

    No Known Activations