© 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. 1-CLT-HP
    7. 10381
    Prev
    Next
    INDEX
    Explanations

    cast

    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
    httphttps
    -0.69
     AppColors
    -0.69
    HasAnnotation
    -0.69
    NameInMap
    -0.65
    ChildScrollView
    -0.62
    UnusedPrivate
    -0.62
    lapsingToolbar
    -0.59
     useRouter
    -0.58
     utafitiHapana
    -0.57
    saraba
    -0.57
    POSITIVE LOGITS
     negoti
    0.47
    Diweddarwch
    0.46
     zus
    0.46
     combines
    0.46
     turns
    0.46
     generates
    0.45
     puts
    0.45
     suits
    0.44
     overcomes
    0.44
     saves
    0.44
    Activations Density 0.016%

    No Known Activations