© 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. 4-CLT-HP
    7. 536
    Prev
    Next
    INDEX
    Explanations

    optical

    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
     BoxFit
    -0.58
    Denomin
    -0.51
    verley
    -0.50
     Gown
    -0.49
     Tomé
    -0.49
    ronesia
    -0.49
     messaggi
    -0.49
    topf
    -0.48
    estanding
    -0.48
    readAs
    -0.48
    POSITIVE LOGITS
    出版年
    0.63
     newBuilder
    0.61
    principalTable
    0.57
    Παραπομπές
    0.54
     onOptions
    0.54
    XmlAccessType
    0.52
    ]")]
    0.51
     '\\;'
    0.51
    JNIEnv
    0.51
    حوالہ
    0.48
    Activations Density 0.008%

    No Known Activations