Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 113
    Prev
    Next
    INDEX
    Explanations

    AM

    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
    AM
    -1.27
     AM
    -1.27
    AMM
    -0.64
    AMS
    -0.61
    原始内容存档于
    -0.58
     am
    -0.53
    AMO
    -0.52
    dle
    -0.52
     AMS
    -0.52
    出版年
    -0.51
    POSITIVE LOGITS
     tewas
    0.54
     Stopped
    0.54
    IonicModule
    0.52
    ihnachts
    0.51
    :“……”
    0.51
    ChrTalk
    0.50
    oredCriteria
    0.50
    StreetMap
    0.50
    احت
    0.50
    PageIndex
    0.49
    Activations Density 0.018%

    No Known Activations