© 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. 1307
    Prev
    Next
    INDEX
    Explanations

    managed

    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
     managed
    -1.56
     Managed
    -1.31
    managed
    -1.30
    Managed
    -1.20
    SourceChecksum
    -1.01
     supervised
    -0.96
     governed
    -0.88
     regulated
    -0.81
     motivated
    -0.79
    DOCTYPE
    -0.77
    POSITIVE LOGITS
     control
    0.61
     the
    0.60
    amu
    0.54
     by
    0.52
     as
    0.52
     proper
    0.52
     their
    0.49
     officials
    0.48
     prí
    0.47
     Control
    0.46
    Activations Density 0.095%

    No Known Activations