© 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. 94655
    Prev
    Next
    INDEX
    Explanations

    Semiconductors/chemical compounds

    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
    dio
    -0.99
    Dio
    -0.99
     dio
    -0.95
     Dio
    -0.91
     Diode
    -0.81
     diode
    -0.80
     whites
    -0.75
     Bioaccumulative
    -0.75
     diodes
    -0.69
    DIO
    -0.68
    POSITIVE LOGITS
    IsContent
    0.76
    bootstrapcdn
    0.69
    InjectAttribute
    0.51
    setViewportView
    0.45
    ígenes
    0.45
    UnusedPrivate
    0.45
     Undeclared
    0.44
     تانيه
    0.43
    chromedriver
    0.42
    Wymiary
    0.42
    Activations Density 1.239%

    No Known Activations