© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2579
    Prev
    Next
    INDEX
    Explanations

    about

    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
     disponibilités
    -0.58
    .
    -0.54
     resourceCulture
    -0.54
    ,
    -0.49
    -
    -0.48
    Distribuzione
    -0.48
     disfr
    -0.45
     and
    -0.45
     disfrute
    -0.45
     Geruch
    -0.45
    POSITIVE LOGITS
    AccessorTable
    0.70
    GOTREF
    0.68
     المعيارى
    0.65
    InputBorder
    0.64
    MLLoader
    0.64
    CodeAttribute
    0.63
     summertime
    0.63
    StructEnd
    0.62
    zzleHttp
    0.61
    ISupport
    0.60
    Activations Density 0.003%

    No Known Activations