© 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. 1-CLT-HP
    7. 593
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    lccn
    -0.55
    éez
    -0.54
    ależy
    -0.51
    ვი
    -0.50
    ]")]
    -0.49
     federally
    -0.48
     ++)
    -0.48
     كومونز
    -0.47
     federal
    -0.47
     الحره
    -0.46
    POSITIVE LOGITS
    COUVER
    0.56
     ostavi
    0.55
    IRUS
    0.54
     ProtoMessage
    0.50
    lichter
    0.50
     '/';
    0.50
    ConstraintMaker
    0.49
     MOQ
    0.49
    '));
    0.49
    forChild
    0.49
    Activations Density 0.022%

    No Known Activations