© 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. 1-CLT-HP
    7. 11918
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     Mela
    -2.50
     mela
    -1.73
    mela
    -1.30
     Mel
    -0.74
    kloped
    -0.73
     ujednoznacz
    -0.71
     disambiguazione
    -0.69
    numerusform
    -0.69
     MEL
    -0.66
     ExecuteAsync
    -0.65
    POSITIVE LOGITS
    urlencoded
    0.58
    setLayoutManager
    0.44
    classnames
    0.43
     Bourgoin
    0.42
    Diz
    0.42
    不思議
    0.41
    водства
    0.41
     Socorro
    0.40
     untersch
    0.39
     volto
    0.39
    Activations Density 0.016%

    No Known Activations