© 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. 97090
    Prev
    Next
    INDEX
    Explanations

    technical compliance, connections

    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
     Compliance
    -0.57
    umptive
    -0.50
     compliance
    -0.48
    umed
    -0.43
    erick
    -0.41
     $
    -0.40
    Compliance
    -0.40
    ё
    -0.40
    ormick
    -0.40
    География
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    0.87
    AndEndTag
    0.85
     protoimpl
    0.74
    AnimationsModule
    0.74
    ểm
    0.73
    UserScript
    0.72
    SBATCH
    0.72
     ausp
    0.70
    abstractmethod
    0.70
    ModelAdmin
    0.70
    Activations Density 1.833%

    No Known Activations