© 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. 1-CLT-HP
    7. 9208
    Prev
    Next
    INDEX
    Explanations

    companies, legal cases, news

    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
     coal
    -1.46
    coal
    -1.34
     Coal
    -1.27
     COAL
    -1.20
    Coal
    -1.16
    COAL
    -0.98
    رشف
    -0.92
     coals
    -0.84
     unknownFields
    -0.81
     otomatig
    -0.70
    POSITIVE LOGITS
     bâ
    0.42
     AdapterView
    0.42
     znan
    0.41
     impré
    0.41
    кина
    0.41
     gratuitement
    0.40
    as
    0.40
     carico
    0.40
    '},
    0.40
    пре
    0.40
    Activations Density 0.160%

    No Known Activations