© 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. 1-CLT-HP
    7. 547
    Prev
    Next
    INDEX
    Explanations

    allergy and ionic compounds

    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
    はじめに
    -0.50
     barras
    -0.49
    ":"+
    -0.48
    EReference
    -0.46
    ANTLR
    -0.45
    unately
    -0.45
     rowspan
    -0.44
     labdar
    -0.43
    inally
    -0.43
     τί
    -0.43
    POSITIVE LOGITS
    ыгана
    0.72
     Normdatei
    0.66
    oredCriteria
    0.65
     Esau
    0.64
    expandindo
    0.63
    elemField
    0.63
     متعلقه
    0.60
     continúas
    0.59
    Amicalement
    0.59
    Ausstattung
    0.58
    Activations Density 0.083%

    No Known Activations