© 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. 5189
    Prev
    Next
    INDEX
    Explanations

    engulfed

    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
     us
    -0.94
     we
    -0.65
     tayo
    -0.61
    We
    -0.60
     нами
    -0.56
    Us
    -0.54
     нас
    -0.54
     нам
    -0.53
    让我们
    -0.52
     kami
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.69
     båda
    0.60
     vieilles
    0.59
     ouvriers
    0.59
    MigrationBuilder
    0.58
    +:+
    0.58
     صوتيه
    0.57
     químicas
    0.56
    XmlAccessorType
    0.56
     zoveel
    0.55
    Activations Density 0.000%

    No Known Activations