© 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. 94874
    Prev
    Next
    INDEX
    Explanations

    Code and web development

    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
    polate
    -0.71
     estekak
    -0.68
    ècie
    -0.64
     ControllerBase
    -0.63
     مشين
    -0.62
    tagHelperRunner
    -0.62
     disambiguazione
    -0.61
    alamus
    -0.59
     виправивши
    -0.59
    MessageOf
    -0.59
    POSITIVE LOGITS
    writeString
    0.49
    w
    0.44
    Shark
    0.41
     anonymous
    0.40
    لاب
    0.40
    ligo
    0.40
    yargs
    0.40
     Shark
    0.40
     σύ
    0.39
     urugu
    0.38
    Activations Density 0.002%

    No Known Activations