© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    oth

    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
    uto
    -1.34
    UTO
    -0.93
    utos
    -0.69
    ACS
    -0.60
    +:+
    -0.59
     Hospice
    -0.59
    ANC
    -0.50
    initial
    -0.49
    Btu
    -0.49
     alluvial
    -0.49
    POSITIVE LOGITS
    expandindo
    0.76
    MigrationBuilder
    0.72
     MainAxisSize
    0.66
    цездатний
    0.65
    httphttps
    0.64
    الإنجليزية
    0.63
    \{\\
    0.61
    archiviato
    0.59
    <?
    0.59
     مشين
    0.57
    Activations Density 0.061%

    No Known Activations