© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45174
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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
     Pristupljeno
    -1.00
    клопе
    -0.98
     nakalista
    -0.94
     चीज़ों
    -0.94
     للاسماء
    -0.91
    kháu
    -0.91
    swire
    -0.89
    polate
    -0.88
     bezeichneter
    -0.87
    הערות
    -0.86
    POSITIVE LOGITS
    -
    0.52
    3
    0.42
    </b>
    0.42
     over
    0.42
     and
    0.41
     
    0.40
    Integer
    0.40
     &
    0.39
     yıld
    0.39
    .
    0.39
    Activations Density 1.289%

    No Known Activations