© 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. 0-CLT-HP
    7. 95048
    Prev
    Next
    INDEX
    Explanations

    Diet

    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
    GEBURTSDATUM
    -0.79
     lifestyle
    -0.78
    Dietary
    -0.75
    calorie
    -0.73
     diet
    -0.73
    Bibliograf
    -0.73
    diet
    -0.72
    }))
    -0.72
     Lifestyle
    -0.71
    })();
    -0.70
    POSITIVE LOGITS
    e
    0.62
    <bos>
    0.59
     Agamemnon
    0.59
     Odysseus
    0.58
     Forderung
    0.57
     ochi
    0.53
     gidi
    0.53
     forgetting
    0.52
     Bergamo
    0.52
     Josephus
    0.52
    Activations Density 0.345%

    No Known Activations