© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96032
    Prev
    Next
    INDEX
    Explanations

    to

    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
     CreateTagHelper
    -0.74
    Personensuche
    -0.54
    scalatest
    -0.53
    存于互联网档案馆
    -0.52
    ]")]
    -0.49
    CopyWith
    -0.48
    xions
    -0.47
    linker
    -0.47
    DotNetBar
    -0.46
     ویکی‌پدیای
    -0.45
    POSITIVE LOGITS
    aarrggbb
    0.57
    Pautan
    0.56
    цездатний
    0.53
    iriman
    0.52
    Билгалдахарш
    0.52
    ConstraintMaker
    0.52
    出版年
    0.51
     eventdata
    0.49
    ̍t
    0.49
    లాలు
    0.48
    Activations Density 0.008%

    No Known Activations