© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96961
    Prev
    Next
    INDEX
    Explanations

    data analysis, language

    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
    ourge
    -0.56
     REIT
    -0.54
    makedirs
    -0.52
    და
    -0.51
     burn
    -0.50
     hate
    -0.50
     ANSWER
    -0.50
    спу
    -0.48
    ngdoc
    -0.48
     Keim
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.68
     Ethn
    0.62
     ethnographic
    0.57
    Boas
    0.56
     ethn
    0.56
    styleType
    0.56
    StructEnd
    0.55
     frequenza
    0.53
    terdam
    0.52
    tivitas
    0.52
    Activations Density 0.002%

    No Known Activations