© 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. 0-CLT-HP
    7. 90812
    Prev
    Next
    INDEX
    Explanations

    official instruction/authorization

    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
     mandate
    -1.10
     mandates
    -1.09
    sibilities
    -0.85
     assignments
    -0.85
     Mandate
    -0.83
     commitments
    -0.79
     mandat
    -0.75
    mand
    -0.73
     beliefs
    -0.67
     jurisdictions
    -0.64
    POSITIVE LOGITS
     Normdatei
    0.76
    omock
    0.74
    ngdoc
    0.68
    DockStyle
    0.64
    ustimmung
    0.64
    AutoField
    0.62
    ganggu
    0.60
    ChildScrollView
    0.59
    RegistryLite
    0.58
    })));
    0.58
    Activations Density 0.091%

    No Known Activations