© 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. 13438
    Prev
    Next
    INDEX
    Explanations

    names

    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
     buying
    -0.42
    nextLine
    -0.40
    elif
    -0.39
     trouvera
    -0.38
     membeli
    -0.38
    INFL
    -0.38
     exact
    -0.37
     Buying
    -0.36
    chtig
    -0.36
    yre
    -0.36
    POSITIVE LOGITS
    الإنجليزية
    0.95
     Савезне
    0.85
     betweenstory
    0.84
    TypedDataSet
    0.79
     kaarangay
    0.78
     kasarigan
    0.76
     يتيمه
    0.73
     Roskov
    0.71
     समीक्षाओं
    0.68
    Carriera
    0.66
    Activations Density 0.013%

    No Known Activations