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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2926
    Prev
    Next
    INDEX
    Explanations

    positive sentiment, legal

    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
    日閲覧
    -0.69
    ftagPool
    -0.68
    脚注の使い方
    -0.59
    +#+#
    -0.57
     Diakses
    -0.54
    =""/>
    -0.53
    )‏
    -0.52
    TestingModule
    -0.49
    Lähteet
    -0.49
    hadapi
    -0.48
    POSITIVE LOGITS
     précis
    0.59
     descriptive
    0.59
     example
    0.58
     description
    0.55
     exemp
    0.52
     encapsulation
    0.52
     depiction
    0.49
     Descriptive
    0.49
     summary
    0.48
    //
    0.48
    Activations Density 0.000%

    No Known Activations