© 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. 91602
    Prev
    Next
    INDEX
    Explanations

    may

    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
    }'.
    -0.56
    خدام
    -0.55
     منها
    -0.55
    reid
    -0.55
     bad
    -0.54
     here
    -0.54
    řeba
    -0.53
     Administrativna
    -0.53
    }".
    -0.52
    ธ์
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.43
    RectangleBorder
    0.43
    ribune
    0.40
     onOptions
    0.40
    ecore
    0.40
    ocracy
    0.39
    TextBoxColumn
    0.37
     DevComponents
    0.37
     BoxDecoration
    0.36
     للمعارف
    0.36
    Activations Density 0.016%

    No Known Activations