© 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. 4634
    Prev
    Next
    INDEX
    Explanations

    names, publications

    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
    <bos>
    -1.20
     ComVisible
    -0.60
    帖最后由
    -0.60
     Italijanski
    -0.60
     utafiti
    -0.60
    WithIOException
    -0.59
     Paglinawan
    -0.58
     архивлан
    -0.56
     Савезне
    -0.56
     Pues
    -0.55
    POSITIVE LOGITS
    ianus
    0.46
    ferous
    0.44
    hofen
    0.43
    ฐ
    0.41
    কার
    0.41
    ogues
    0.41
    CLE
    0.41
    renar
    0.40
    azin
    0.40
    Legende
    0.39
    Activations Density 0.013%

    No Known Activations