© 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. 45446
    Prev
    Next
    INDEX
    Explanations

    units of measurement/time

    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
    .
    -0.46
     вы
    -0.45
     p
    -0.44
     --
    -0.43
    enez
    -0.43
    imbur
    -0.42
    anceled
    -0.42
     quelli
    -0.42
    rs
    -0.42
    eds
    -0.42
    POSITIVE LOGITS
     myſelf
    0.97
    MigrationBuilder
    0.89
     cdti
    0.87
    spesies
    0.85
     itſelf
    0.82
     الرياضيه
    0.81
     crdi
    0.79
     Reſ
    0.79
     meriva
    0.79
     ſtate
    0.78
    Activations Density 0.163%

    No Known Activations