© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2353
    Prev
    Next
    INDEX
    Explanations

    years/version numbers

    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
    tagHelperRunner
    -0.74
    UnknownFieldSet
    -0.66
    endphp
    -0.62
    ⁡
    -0.61
    expandindo
    -0.59
    ┻
    -0.59
    UserScript
    -0.57
     corona
    -0.56
     coronavirus
    -0.56
    Component
    -0.55
    POSITIVE LOGITS
     RouterModule
    0.59
    @[+][
    0.57
     officiels
    0.55
     freio
    0.54
    following
    0.54
     مرئيه
    0.54
     seguinte
    0.53
     roulant
    0.52
     présidenti
    0.52
     following
    0.52
    Activations Density 0.014%

    No Known Activations