© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1343
    Prev
    Next
    INDEX
    Explanations

    random text snippets

    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
     plant
    -0.91
     ujednoznacz
    -0.90
    iosync
    -0.79
    ulatum
    -0.78
     Plant
    -0.76
    æus
    -0.72
    plant
    -0.70
    Plant
    -0.70
     وتسجيلات
    -0.65
    lants
    -0.64
    POSITIVE LOGITS
     photolibrary
    0.74
     "];
    0.66
    ">—
    0.65
     ]
    0.63
     Италијани
    0.61
    en
    0.60
    fulness
    0.57
    er
    0.57
    ỡng
    0.57
    ()))
    0.57
    Activations Density 0.076%

    No Known Activations