© 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. 20-CLT-HP
    7. 72163
    Prev
    Next
    INDEX
    Explanations

    file names

    np_max-act-logits · 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
    RegistryLite
    -0.69
    Искәрмәләр
    -0.68
    tahui
    -0.56
    Notae
    -0.55
    DIPSETTING
    -0.54
    GOTREF
    -0.53
    setupUi
    -0.52
    adpleegd
    -0.52
    ArrowToggle
    -0.51
     etek
    -0.50
    POSITIVE LOGITS
     DATE
    0.55
    dates
    0.51
     dates
    0.50
     VIT
    0.50
    DATE
    0.50
    VIT
    0.48
     locaux
    0.48
    IED
    0.47
     Scoop
    0.47
     dessus
    0.47
    Activations Density 0.001%

    No Known Activations