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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91065
    Prev
    Next
    INDEX
    Explanations

    memory

    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
     memory
    -1.30
     Memory
    -1.04
    memory
    -0.97
    Memory
    -0.91
     MEMORY
    -0.89
     mémoire
    -0.69
     memories
    -0.66
     memória
    -0.65
     memoria
    -0.64
    MEMORY
    -0.64
    POSITIVE LOGITS
     Савезне
    0.77
     initComponents
    0.70
     autorytatywna
    0.66
    <bos>
    0.57
    FormTagHelper
    0.56
    onAttach
    0.56
    extAlignment
    0.56
    帖最后由
    0.55
    CodedInputStream
    0.55
    imakasih
    0.54
    Activations Density 0.057%

    No Known Activations