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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43331
    Prev
    Next
    INDEX
    Explanations

    political/legal matters

    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
     winds
    -1.20
     wind
    -1.16
     laws
    -1.13
    winds
    -1.05
     legislation
    -1.00
     WIND
    -0.99
    Wind
    -0.97
     win
    -0.93
     Winds
    -0.93
     Winding
    -0.92
    POSITIVE LOGITS
     intptr
    0.60
    ArrowToggle
    0.54
    thâu
    0.54
    はじめに
    0.51
    PROTOBUF
    0.50
    XtraBars
    0.49
     useContext
    0.48
    fertigung
    0.46
    hawatir
    0.45
    ristiano
    0.44
    Activations Density 0.041%

    No Known Activations