© 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. 20-CLT-HP
    7. 71740
    Prev
    Next
    INDEX
    Explanations

    code/reports/documents

    np_max-act-logits · 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
    Explanation
    -0.60
    gtest
    -0.59
     Arrondissement
    -0.58
    dese
    -0.57
    Personendaten
    -0.57
    kmale
    -0.56
    endphp
    -0.56
     roze
    -0.56
    onView
    -0.55
     Divide
    -0.54
    POSITIVE LOGITS
    ValueStyle
    0.57
    AsUp
    0.51
    chyma
    0.47
    awt
    0.45
    emia
    0.45
    bindValue
    0.45
    Tikang
    0.43
     tæt
    0.43
    ônia
    0.43
     keuken
    0.41
    Activations Density 0.003%

    No Known Activations