© 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. 351
    Prev
    Next
    INDEX
    Explanations

    Code/Technology/Internet

    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
     purpoſe
    -0.77
     ſtre
    -0.66
     houſe
    -0.64
     Anſ
    -0.64
     deſt
    -0.63
     themſelves
    -0.62
     raiſ
    -0.62
     ſta
    -0.61
     whoſe
    -0.61
    Спољашње
    -0.61
    POSITIVE LOGITS
    MigrationBuilder
    0.62
     Q
    0.58
    Q
    0.56
    QP
    0.55
     Kenney
    0.54
    findpost
    0.54
    GEBURTS
    0.52
    providedIn
    0.50
     q
    0.50
    odine
    0.50
    Activations Density 0.003%

    No Known Activations