© 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. 5-CLT-HP
    7. 94647
    Prev
    Next
    INDEX
    Explanations

    might

    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
    ########.
    -0.60
     صوتيه
    -0.59
    MigrationBuilder
    -0.59
    GraphicsUnit
    -0.57
     betweenstory
    -0.56
     <=",
    -0.56
    dersfield
    -0.56
    出版年
    -0.56
    İstinadlar
    -0.55
     fieldNum
    -0.54
    POSITIVE LOGITS
     will
    0.64
    will
    0.57
     Will
    0.56
    Will
    0.53
     sẽ
    0.51
    จะ
    0.50
     volna
    0.49
    채
    0.48
    会
    0.48
    天的
    0.48
    Activations Density 0.000%

    No Known Activations