© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10672
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    ItemBackground
    -0.79
     <=",
    -0.74
    참고
    -0.73
    DrawerToggle
    -0.73
     通販
    -0.72
    AnchorStyles
    -0.68
    writerow
    -0.66
    contentLoaded
    -0.66
    Gdx
    -0.65
     rhestr
    -0.65
    POSITIVE LOGITS
     Harrison
    0.55
    Harrison
    0.44
    Kos
    0.42
     Treff
    0.40
    Com
    0.37
     exactly
    0.36
     anything
    0.36
     nothing
    0.36
     immortality
    0.36
     HARRISON
    0.36
    Activations Density 0.064%

    No Known Activations