© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    reference

    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
     Вікі
    -0.73
     GenerationType
    -0.65
    Aholisi
    -0.56
     gynhyrchwyd
    -0.54
    AddHtmlAttribute
    -0.54
     khảo
    -0.54
    ⓘ
    -0.54
     disambiguazione
    -0.53
    PreferredItem
    -0.53
     يتيمه
    -0.52
    POSITIVE LOGITS
    KEYCODE
    0.48
    IsContent
    0.47
    ttino
    0.45
    ContentAsync
    0.45
    YEN
    0.44
     protoimpl
    0.44
    ADELPHIA
    0.44
    cinct
    0.43
    Clik
    0.43
    verket
    0.42
    Activations Density 0.000%

    No Known Activations