© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97719
    Prev
    Next
    INDEX
    Explanations

    documents and papers

    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
    emptory
    -2.14
     surla
    -0.68
    hasMoreElements
    -0.63
    StructEnd
    -0.60
     للمعارف
    -0.58
    Portail
    -0.56
     kohdetta
    -0.56
    vimento
    -0.54
    er
    -0.52
    initializeApp
    -0.52
    POSITIVE LOGITS
    NGC
    0.61
    Hozzáférés
    0.57
    PMailer
    0.57
    indor
    0.51
    CppMethod
    0.49
    optarg
    0.48
    chitz
    0.48
     seizure
    0.46
     Himo
    0.46
    pricht
    0.45
    Activations Density 0.088%

    No Known Activations