© 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. 5-CLT-HP
    7. 5506
    Prev
    Next
    INDEX
    Explanations

    code

    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
    wpdb
    -0.55
    IAL
    -0.47
     Spec
    -0.47
    fetchone
    -0.46
     jScrollPane
    -0.46
    ial
    -0.45
     '&#
    -0.44
     spec
    -0.44
     SCS
    -0.43
    uating
    -0.43
    POSITIVE LOGITS
    mybatisplus
    0.79
     propOrder
    0.75
     disambiguazione
    0.71
     Signalez
    0.70
     Roskov
    0.69
    parsedMessage
    0.66
    abstractmethod
    0.62
    UnsafeEnabled
    0.62
     tarko
    0.60
    seamnă
    0.59
    Activations Density 0.002%

    No Known Activations