© 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. 3723
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
    Personendaten
    -1.21
    تقاوى
    -1.13
    zzleHttp
    -1.00
     otomatig
    -0.99
     propOrder
    -0.98
    webElementXpaths
    -0.96
    ImageContext
    -0.95
    mybatisplus
    -0.95
    UnusedPrivate
    -0.93
    styleType
    -0.89
    POSITIVE LOGITS
    ところです
    0.41
    en
    0.38
    #
    0.37
    aka
    0.37
    cz
    0.37
    ↵↵
    0.36
     micro
    0.36
    i
    0.36
    us
    0.35
    li
    0.35
    Activations Density 0.037%

    No Known Activations