© 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. 0-CLT-HP
    7. 93506
    Prev
    Next
    INDEX
    Explanations

    legal/technical contexts

    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
    存于互联网档案馆
    -0.88
    stones
    -0.85
     itſelf
    -0.84
     Normdatei
    -0.83
     ویکی‌پدیا
    -0.81
    XmlAccessorType
    -0.76
     myſelf
    -0.76
     stones
    -0.75
     theſe
    -0.75
    resave
    -0.75
    POSITIVE LOGITS
     he
    0.50
     Application
    0.50
     gener
    0.48
     Link
    0.46
     Enter
    0.46
    intre
    0.45
     Anderson
    0.45
     grig
    0.45
     pel
    0.44
     Links
    0.43
    Activations Density 0.747%

    No Known Activations