© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3719
    Prev
    Next
    INDEX
    Explanations

    card

    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
     tightly
    -0.51
    isHidden
    -0.45
    にあります
    -0.45
     relatively
    -0.43
     lenker
    -0.41
     contained
    -0.41
     tight
    -0.41
    Storing
    -0.41
    ългария
    -0.40
     rapat
    -0.40
    POSITIVE LOGITS
     nakalista
    0.81
     noDo
    0.77
    最快更新
    0.71
     unknownFields
    0.70
     sherds
    0.69
     betweenstory
    0.68
    ObjectContext
    0.67
    spesies
    0.67
     дописавши
    0.67
    出版年
    0.66
    Activations Density 0.002%

    No Known Activations